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

    Neuronpedia

    INDEX
    Explanations

    references to libraries and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igg
    -0.16
    allah
    -0.16
    ½
    -0.15
    748
    -0.15
    oo
    -0.15
    ):?>↵
    -0.14
    aida
    -0.14
    away
    -0.14
    ivas
    -0.13
    еÑĨ
    -0.13
    POSITIVE LOGITS
    yard
    0.18
    istics
    0.15
    iod
    0.15
    alet
    0.15
    aeper
    0.15
    oppins
    0.15
    çķ
    0.14
    visor
    0.14
    izontal
    0.14
    yards
    0.14
    Act Density 0.019%

    No Known Activations