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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to personal characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    present tense and past tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anos
    -0.66
     Inqu
    -0.56
    raltar
    -0.55
    pheus
    -0.54
    zan
    -0.53
    iken
    -0.52
     inquiries
    -0.51
    ERY
    -0.51
     scraps
    -0.51
    INC
    -0.50
    POSITIVE LOGITS
     compared
    0.91
     relative
    0.78
    Interstitial
    0.78
     supposed
    0.73
    .
    0.72
     nowadays
    0.69
     regarding
    0.69
    !.
    0.69
     unto
    0.67
     against
    0.67
    Act Density 0.091%

    No Known Activations