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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions and language indicating action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lad
    -0.15
    Ģìŀ¥
    -0.15
    Mesh
    -0.14
    ANGO
    -0.14
    ango
    -0.14
    å¹¹
    -0.14
    ajo
    -0.14
    astics
    -0.13
     ARR
    -0.13
    ored
    -0.13
    POSITIVE LOGITS
    ıklı
    0.15
    iguiente
    0.14
    _SPEC
    0.14
    ville
    0.14
    iswa
    0.14
    ourcem
    0.13
    ÑģÑı
    0.13
    piar
    0.13
    .AutoScaleMode
    0.13
     vig
    0.13
    Act Density 0.030%

    No Known Activations