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

    Neuronpedia

    INDEX
    Explanations

    words related to causality, particularly indicating what propels or triggers certain actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate causation or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFT
    -0.69
    urai
    -0.66
     Blackwell
    -0.58
    bral
    -0.56
     Kinnikuman
    -0.56
    oos
    -0.55
    çĦ
    -0.55
     Haku
    -0.54
    ift
    -0.54
     Recon
    -0.54
    POSITIVE LOGITS
     by
    1.39
    by
    1.27
    By
    1.04
     BY
    0.97
     By
    0.94
     partly
    0.92
     principally
    0.92
    BY
    0.89
     chiefly
    0.86
     solely
    0.85
    Act Density 0.209%

    No Known Activations