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

    Neuronpedia

    INDEX
    Explanations

    references to restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ically
    -0.17
    bing
    -0.16
    neau
    -0.15
    ingham
    -0.15
    hound
    -0.15
    wich
    -0.15
    kar
    -0.14
    anel
    -0.14
    eparator
    -0.14
    yc
    -0.14
    POSITIVE LOGITS
    rophe
    0.25
     Liability
    0.25
     edition
    0.22
     scope
    0.22
     liability
    0.21
    lessly
    0.21
    iations
    0.20
     LIABILITY
    0.20
    -ed
    0.19
     sayıda
    0.19
    Act Density 0.055%

    No Known Activations