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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal claims and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carlin
    -0.91
    kates
    -0.79
    Demografia
    -0.76
     Sis
    -0.74
    ofday
    -0.73
     latter
    -0.69
     come
    -0.69
    mw
    -0.68
     Bigelow
    -0.68
    ^(@)
    -0.67
    POSITIVE LOGITS
    ing
    1.80
    ING
    1.18
     Reject
    0.91
    Accept
    0.89
     encrypt
    0.85
     Employ
    0.84
     Deliver
    0.83
     Agree
    0.83
    Disagree
    0.83
    Deliver
    0.83
    Act Density 0.304%

    No Known Activations