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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and related representations

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     antioxid
    -1.08
    Balt
    -0.84
    RESULTS
    -0.79
     ingred
    -0.74
     behavi
    -0.74
     corrid
    -0.71
     adolesc
    -0.70
    OHN
    -0.70
    ROR
    -0.69
    SPONSORED
    -0.68
    POSITIVE LOGITS
    ividual
    0.81
     ItemLevel
    0.75
    itially
    0.74
    ogun
    0.72
    enfranch
    0.68
    rue
    0.67
    ecause
    0.67
    othal
    0.65
    mosp
    0.63
    rike
    0.63
    Act Density 11.747%

    No Known Activations