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

    Neuronpedia

    INDEX
    Explanations

    adjectives with a negative connotation or related to conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulation and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     examiner
    -0.51
     governor
    -0.51
     Welsh
    -0.50
     family
    -0.50
     comma
    -0.50
     nickname
    -0.49
     filing
    -0.48
     assemblies
    -0.47
     inspector
    -0.47
     notebook
    -0.47
    POSITIVE LOGITS
    ited
    0.82
    ibly
    0.81
    inged
    0.81
    vered
    0.80
    eded
    0.77
    icating
    0.77
    arily
    0.76
    alled
    0.76
    iably
    0.75
    icked
    0.75
    Act Density 0.430%

    No Known Activations