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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases starting with "in the" that refer to a significant scope or scale

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a scheme or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >>>>>>>>
    -0.75
    .–
    -0.73
    >(
    -0.73
    ................................................................
    -0.72
    />
    -0.72
     Flavoring
    -0.68
    NetMessage
    -0.64
     />
    -0.63
    escription
    -0.62
    ................................
    -0.60
    POSITIVE LOGITS
     fame
    0.60
    tnc
    0.60
     persuasion
    0.59
     professions
    0.59
    viron
    0.59
     Nations
    0.58
     hindsight
    0.57
     Sciences
    0.56
    sight
    0.55
     infancy
    0.55
    Act Density 0.346%

    No Known Activations