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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific location indicators or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrera
    -0.15
    ans
    -0.15
    onor
    -0.15
    orny
    -0.15
    arus
    -0.15
    andles
    -0.15
    odÃŃ
    -0.14
    enta
    -0.14
    OST
    -0.14
    iens
    -0.14
    POSITIVE LOGITS
    ovel
    0.17
    ague
    0.15
    rip
    0.14
    adolu
    0.13
    еÑĦ
    0.13
    Ñĩна
    0.13
    -ms
    0.13
    avel
    0.13
     Dial
    0.13
     Dash
    0.13
    Act Density 0.060%

    No Known Activations