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

    Neuronpedia

    INDEX
    Explanations

    mentions of societal issues and personal grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Levin
    -0.15
    bourg
    -0.15
    hoo
    -0.15
    h
    -0.15
     Starter
    -0.14
     fis
    -0.14
    cons
    -0.14
     fiscal
    -0.13
     -
    -0.13
    onen
    -0.13
    POSITIVE LOGITS
    phia
    0.19
    aterangepicker
    0.16
    ToProps
    0.15
    íĥĪ
    0.14
    atis
    0.14
    rane
    0.14
    pun
    0.14
    tel
    0.14
    aln
    0.14
    Yaw
    0.14
    Act Density 0.018%

    No Known Activations