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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news and events coverage

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to counterproductive actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -0.96
    RESULTS
    -0.80
     ingred
    -0.70
    OHN
    -0.70
    Balt
    -0.68
    SPONSORED
    -0.66
    ROR
    -0.64
     enthusi
    -0.64
     pestic
    -0.63
    IDA
    -0.62
    POSITIVE LOGITS
     ItemLevel
    0.74
    enfranch
    0.74
    itially
    0.72
    mosp
    0.72
    rue
    0.71
    ividual
    0.71
    rike
    0.70
    ogun
    0.67
    ilege
    0.65
     BaseType
    0.63
    Act Density 12.545%

    No Known Activations