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

    Neuronpedia

    INDEX
    Explanations

    interactions that involve requests for feedback or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a polite request

    np_acts-logits-general · gemini-2.0-flash

    please contact or ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rosal
    -0.51
     ErrIntOverflow
    -0.51
     AdapterView
    -0.48
    DockStyle
    -0.48
     WHEREAS
    -0.47
    kloped
    -0.47
     podjela
    -0.46
     Richelieu
    -0.45
    といけない
    -0.45
     málo
    -0.44
    POSITIVE LOGITS
     PM
    1.06
     send
    0.96
     Send
    0.93
     contact
    0.92
     pm
    0.90
     DM
    0.88
    PM
    0.86
     shoot
    0.83
     feel
    0.83
    Send
    0.82
    Act Density 0.159%

    No Known Activations