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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in '-ly'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe actions or qualities emphatically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.79
    VL
    -0.77
    OTOS
    -0.70
     LH
    -0.68
    INC
    -0.67
     sockets
    -0.66
    afety
    -0.66
    istor
    -0.64
    itu
    -0.63
    ession
    -0.63
    POSITIVE LOGITS
     titled
    0.78
     performed
    0.76
     entertained
    0.75
     paced
    0.71
    forth
    0.71
     employed
    0.71
    yy
    0.71
    beit
    0.70
    bus
    0.70
     discharged
    0.69
    Act Density 0.067%

    No Known Activations