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

    Neuronpedia

    INDEX
    Explanations

    references to significant changes and transformations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONO
    -0.14
    itorio
    -0.14
    udge
    -0.14
     vit
    -0.14
     manner
    -0.14
     Mand
    -0.14
    MAND
    -0.14
    /thumb
    -0.14
    ouve
    -0.13
    ono
    -0.13
    POSITIVE LOGITS
    (change
    0.17
    -change
    0.17
    sworth
    0.16
    áng
    0.16
    (changes
    0.16
    ìĤ¬íķŃ
    0.16
    ÑĢÑı
    0.15
    ãģĻãģİ
    0.15
     change
    0.15
    /change
    0.15
    Act Density 0.406%

    No Known Activations