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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to consequences and ethical dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -1.17
     behavi
    -1.01
    OHN
    -0.91
    Balt
    -0.89
     ingred
    -0.86
    PDATE
    -0.86
    RESULTS
    -0.85
     adolesc
    -0.84
    ROR
    -0.84
     enthusi
    -0.84
    POSITIVE LOGITS
    itially
    0.79
    ividual
    0.76
     ItemLevel
    0.75
    rue
    0.72
    ogun
    0.70
    enfranch
    0.70
    agate
    0.68
    othal
    0.65
     BaseType
    0.64
    ilege
    0.63
    Act Density 5.337%

    No Known Activations