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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or similarity

    oai_token-act-pair · gpt-3.5-turbo

    auxiliary verbs indicating actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QB
    -0.73
    opian
    -0.66
    dream
    -0.66
    colo
    -0.65
    jab
    -0.64
    OH
    -0.63
    Words
    -0.62
    places
    -0.60
     incorpor
    -0.59
     bip
    -0.58
    POSITIVE LOGITS
     Geh
    0.72
     others
    0.66
     countless
    0.65
    racuse
    0.63
    essage
    0.63
     Doomsday
    0.61
     Greenberg
    0.61
    SHARE
    0.60
    OTAL
    0.59
     dozens
    0.59
    Act Density 0.044%

    No Known Activations