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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government actions or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owan
    -0.78
     belongs
    -0.73
     Kills
    -0.67
    itars
    -0.63
    odied
    -0.63
     greatness
    -0.62
    ulence
    -0.60
    pered
    -0.60
     fades
    -0.60
    ":[{"
    -0.60
    POSITIVE LOGITS
     hoping
    1.34
     eyeing
    1.26
     preparing
    1.24
     planning
    1.21
     expecting
    1.18
     gearing
    1.18
     investigating
    1.18
     proposing
    1.16
     scrambling
    1.15
     considering
    1.14
    Act Density 0.173%

    No Known Activations