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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and verbs indicating actions or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olini
    -0.64
    rick
    -0.64
    lis
    -0.63
    PDATE
    -0.62
    liner
    -0.61
    zel
    -0.59
    zan
    -0.57
    Enlarge
    -0.57
    SON
    -0.55
    ston
    -0.55
    POSITIVE LOGITS
    a
    1.10
     a
    1.08
     A
    0.88
    A
    0.79
     an
    0.74
    aa
    0.71
    ai
    0.70
     Ãł
    0.69
    Ãł
    0.67
    ae
    0.66
    Act Density 0.205%

    No Known Activations