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

    Neuronpedia

    INDEX
    Explanations

    words related to actions performed with a specific attitude or approach, such as 'governmentally' or 'behaviourally'

    oai_token-act-pair · gpt-3.5-turbo

    the word "ally" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.79
    lda
    -0.76
     Pirate
    -0.71
     Julio
    -0.70
    alities
    -0.66
    nce
    -0.66
     Jarvis
    -0.66
     Struggle
    -0.64
     Parenthood
    -0.64
    orters
    -0.64
    POSITIVE LOGITS
     minded
    1.02
    uminum
    0.81
     speaking
    0.78
    abama
    0.75
     gland
    0.73
     paced
    0.73
    minded
    0.70
    uters
    0.69
    gage
    0.69
    cock
    0.69
    Act Density 0.018%

    No Known Activations