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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crime, law enforcement, and legal procedures

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to individuals involved in a specific event or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.81
    ccording
    -0.79
    ership
    -0.75
    ers
    -0.72
    orses
    -0.69
    orable
    -0.65
    olulu
    -0.63
    est
    -0.62
    edit
    -0.60
     challeng
    -0.60
    POSITIVE LOGITS
    bilt
    1.09
    jee
    1.01
    idge
    1.01
    geist
    1.00
    lein
    0.99
    iffe
    0.92
    clips
    0.91
    getic
    0.89
    baum
    0.88
    wald
    0.86
    Act Density 0.155%

    No Known Activations