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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rarity or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of significant need or change within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stall
    -0.78
     bec
    -0.66
    Jet
    -0.64
     Mub
    -0.63
    fen
    -0.63
    ãĥīãĥ©
    -0.60
    hai
    -0.58
    backer
    -0.58
    Plan
    -0.57
    dial
    -0.56
    POSITIVE LOGITS
     EVER
    0.75
     imaginable
    0.71
     ever
    0.69
     occasion
    0.68
     humankind
    0.67
     mankind
    0.65
     presidents
    0.65
     occasions
    0.63
     recorded
    0.62
     happier
    0.62
    Act Density 0.219%

    No Known Activations