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

    Neuronpedia

    INDEX
    Explanations

    structured descriptions or definitions of components or elements within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Away
    -0.16
    Away
    -0.16
    Ģìŀ¥
    -0.16
    ish
    -0.15
    ава
    -0.15
    aln
    -0.14
    ille
    -0.14
    quets
    -0.14
    olor
    -0.14
    ortal
    -0.14
    POSITIVE LOGITS
     entirely
    0.25
    antly
    0.21
     consist
    0.20
     Ñģобой
    0.20
     consists
    0.19
     comprised
    0.19
     consisted
    0.18
     largely
    0.17
     consisting
    0.17
    encies
    0.17
    Act Density 0.018%

    No Known Activations