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

    Neuronpedia

    INDEX
    Explanations

    verbs related to expressing beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to declarations or statements of belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sahara
    -0.75
    HCR
    -0.68
     Jade
    -0.65
     Townsend
    -0.62
     Seah
    -0.62
     cooker
    -0.61
     agile
    -0.61
     crest
    -0.60
     Avalon
    -0.60
    displayText
    -0.60
    POSITIVE LOGITS
     profess
    1.21
    orial
    1.18
    orship
    1.13
    edIn
    1.00
    edly
    0.99
    enstein
    0.91
    es
    0.90
    urous
    0.87
    eking
    0.84
    entimes
    0.84
    Act Density 0.008%

    No Known Activations