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

    Neuronpedia

    INDEX
    Explanations

    negations and disclaimers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.15
    allen
    -0.15
    ycastle
    -0.15
    iam
    -0.15
    ITED
    -0.14
    orian
    -0.14
    acier
    -0.14
     transplant
    -0.14
    pu
    -0.13
    651
    -0.13
    POSITIVE LOGITS
    hangi
    0.18
    uml
    0.15
    енÑĤÑĥ
    0.14
    dale
    0.14
     other
    0.14
    -addons
    0.14
    esel
    0.14
    ÄŁit
    0.14
    èĢ
    0.13
    asca
    0.13
    Act Density 0.190%

    No Known Activations