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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assistance or support provided by one party to another

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    alde
    -0.70
    pora
    -0.67
     WATCHED
    -0.64
    AH
    -0.63
    puff
    -0.62
    dayName
    -0.62
    =#
    -0.60
    anwhile
    -0.60
    oppable
    -0.59
    inators
    -0.59
    POSITIVE LOGITS
     cred
    0.97
     lend
    0.87
     lending
    0.85
     lent
    0.80
     generously
    0.79
     assistance
    0.77
     aid
    0.74
    shire
    0.74
     insight
    0.71
    ancing
    0.71
    Act Density 0.017%

    No Known Activations