Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 609
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing and receiving information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mine
    -0.75
    bery
    -0.73
    cius
    -0.70
    une
    -0.70
    ocard
    -0.69
    pid
    -0.68
    uristic
    -0.66
    othermal
    -0.65
    ATURE
    -0.64
     restroom
    -0.64
    POSITIVE LOGITS
    -+-+
    0.66
    龍契士
    0.60
     Returning
    0.60
     opted
    0.60
     choices
    0.60
    ��
    0.59
    akings
    0.58
     Rising
    0.58
    1001
    0.57
     Scouting
    0.57
    Activations Density 0.015%

    No Known Activations