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

    Neuronpedia

    INDEX
    Explanations

    terms related to communication and notification methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stein
    -0.79
     marrow
    -0.77
    bart
    -0.76
    bard
    -0.75
    hani
    -0.73
    teen
    -0.72
    ffen
    -0.71
    theless
    -0.70
    abama
    -0.67
    女
    -0.63
    POSITIVE LOGITS
    Cs
    0.81
    IDs
    0.79
     messages
    0.78
    ES
    0.77
    ARS
    0.75
     Messages
    0.74
    encing
    0.74
    DAQ
    0.73
    Message
    0.71
    rams
    0.71
    Act Density 0.005%

    No Known Activations