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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to identification and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.88
    mic
    -0.80
    roc
    -0.79
    roll
    -0.75
    shape
    -0.75
    stant
    -0.74
    ordinate
    -0.73
    wind
    -0.72
    rop
    -0.71
    lins
    -0.71
    POSITIVE LOGITS
     identification
    0.83
    anguage
    0.82
     authorization
    0.78
    ary
    0.78
     Assistance
    0.77
     scheme
    0.77
    eering
    0.76
     acknowledgement
    0.76
     Authorization
    0.75
     schemes
    0.74
    Act Density 0.035%

    No Known Activations