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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states that are strong or impactful

    oai_token-act-pair · gpt-3.5-turbo

    words related to appropriateness and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bard
    -0.65
    BuyableInstoreAndOnline
    -0.65
     challeng
    -0.63
    ulhu
    -0.63
    minster
    -0.61
    CHO
    -0.60
    ACP
    -0.59
    Bloom
    -0.59
    CHR
    -0.59
     mosqu
    -0.59
    POSITIVE LOGITS
    ibly
    1.22
    itely
    1.11
    ities
    1.07
    ately
    1.07
    aneously
    1.04
    aneous
    1.03
    hement
    1.02
    ously
    1.01
    able
    1.00
    iencies
    1.00
    Act Density 0.203%

    No Known Activations