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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assigning causes or reasons to specific situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to causation and attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lite
    -0.80
    aspx
    -0.77
    ceans
    -0.69
    lake
    -0.68
    enegger
    -0.66
    corn
    -0.66
    ierre
    -0.63
    kat
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    estern
    -0.62
    POSITIVE LOGITS
     attribut
    0.93
     blame
    0.91
     Attribution
    0.79
    ribed
    0.78
     attribution
    0.75
     attributed
    0.71
    lled
    0.70
     charism
    0.69
    ithe
    0.69
    unct
    0.68
    Act Density 0.022%

    No Known Activations