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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.74
    gang
    -0.72
    entimes
    -0.69
    die
    -0.66
     conveyed
    -0.60
    yip
    -0.60
     insulted
    -0.59
    ice
    -0.58
     summons
    -0.58
    cpu
    -0.58
    POSITIVE LOGITS
     adulthood
    1.13
     orbit
    0.94
    jected
    0.83
     unch
    0.82
    clusion
    0.80
     Valhalla
    0.78
    clusions
    0.77
    veyard
    0.77
    jection
    0.76
     existence
    0.76
    Act Density 1.119%

    No Known Activations