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

    Neuronpedia

    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to significant years or historical dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Topic
    -0.65
     Sym
    -0.62
    Maker
    -0.61
    Topics
    -0.61
     Dil
    -0.58
    lication
    -0.57
     Jugg
    -0.56
     Surface
    -0.56
     Breath
    -0.55
     thirsty
    -0.55
    POSITIVE LOGITS
    uberty
    0.77
    azo
    0.75
    uly
    0.75
    iatus
    0.73
    irtual
    0.72
    ties
    0.70
    vez
    0.68
    izons
    0.66
    ratch
    0.65
    rapnel
    0.64
    Act Density 0.093%

    No Known Activations