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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical conditions or states of weakness

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with weakness and subtlety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeau
    -0.73
    gemony
    -0.70
    POR
    -0.66
    PUT
    -0.64
     Cosponsors
    -0.63
    oldown
    -0.63
    aminer
    -0.63
    uliffe
    -0.62
    Western
    -0.62
    rients
    -0.62
    POSITIVE LOGITS
     faint
    1.09
    est
    0.82
    lings
    0.80
     glow
    0.79
     remnant
    0.78
    hearted
    0.73
     blinking
    0.71
    nesses
    0.71
    igible
    0.69
    escription
    0.68
    Act Density 0.007%

    No Known Activations