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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "BS" referring to a specific topic or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Detail
    -0.65
     Sphere
    -0.61
     defining
    -0.61
     Ceres
    -0.60
     Cheong
    -0.59
     generation
    -0.57
     Hipp
    -0.56
     establishment
    -0.56
     Avalon
    -0.55
     Marino
    -0.55
    POSITIVE LOGITS
    ettings
    1.17
    ession
    1.02
    ITE
    0.93
    BS
    0.91
    ESSION
    0.87
    AME
    0.87
    KI
    0.87
    ombat
    0.85
    CRIP
    0.84
    wana
    0.84
    Act Density 0.015%

    No Known Activations