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

    Neuronpedia

    INDEX
    Explanations

    causal relationships or explanations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.77
     كومونز
    -0.77
    tagHelperRunner
    -0.73
    httphttps
    -0.73
    🏾
    -0.69
    verständlich
    -0.68
    Autoritní
    -0.67
    🏻
    -0.65
     surla
    -0.64
    ).__
    -0.64
    POSITIVE LOGITS
     Causes
    1.05
     CAUSE
    1.02
     Cause
    0.99
    causes
    0.97
     causes
    0.96
     cause
    0.92
    Causes
    0.90
     caused
    0.89
     Caus
    0.85
     caus
    0.85
    Act Density 0.111%

    No Known Activations