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

    Neuronpedia

    INDEX
    Explanations

    timestamps or locations in text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of numerical values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citiz
    -0.79
     submar
    -0.70
     bom
    -0.70
     Nare
    -0.69
    abwe
    -0.68
    undai
    -0.68
     destro
    -0.68
     sovere
    -0.66
     streng
    -0.64
     outsourcing
    -0.64
    POSITIVE LOGITS
    ALT
    0.88
    Reviewed
    0.84
    Posted
    0.84
    ////////////////////////////////
    0.83
     SHARES
    0.82
     largeDownload
    0.80
    LIN
    0.79
    Minecraft
    0.79
    Flight
    0.79
    Introduction
    0.77
    Act Density 0.078%

    No Known Activations