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

    Neuronpedia

    INDEX
    Explanations

    political and legal terms or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .","
    -0.82
     ..."
    -0.75
     ('
    -0.74
     \"
    -0.73
    )</
    -0.71
     �
    -0.69
     -->
    -0.67
    ().
    -0.64
    .</
    -0.64
    >]
    -0.60
    POSITIVE LOGITS
    odore
    1.06
    resa
    1.02
    withstanding
    0.97
    xiety
    0.91
    notations
    0.79
    pherd
    0.79
    wards
    0.78
    romeda
    0.78
    zbollah
    0.78
    omsky
    0.77
    Act Density 0.607%

    No Known Activations