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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong willingness or effort to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.75
     Debor
    -0.67
     EUR
    -0.63
    BuyableInstoreAndOnline
    -0.62
     Lauder
    -0.61
    pered
    -0.60
    ERY
    -0.59
    hran
    -0.58
    ELD
    -0.56
    closed
    -0.56
    POSITIVE LOGITS
     muster
    1.11
     afford
    1.02
     manage
    0.88
     possibly
    0.88
     feas
    0.84
     tolerate
    0.82
    berra
    0.81
     achieve
    0.81
     conceive
    0.80
    't
    0.77
    Act Density 0.048%

    No Known Activations