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

    Neuronpedia

    INDEX
    Explanations

    elements related to potential outcomes and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    638
    -0.14
    \Mapping
    -0.14
     Peak
    -0.14
     Survival
    -0.14
    aper
    -0.14
    ourage
    -0.13
    ourcem
    -0.13
    eri
    -0.13
    ecta
    -0.13
    ari
    -0.13
    POSITIVE LOGITS
    dik
    0.16
    avar
    0.15
    kers
    0.15
    rive
    0.14
     Hawk
    0.14
    éric
    0.14
    ków
    0.14
    lak
    0.13
    Ïĩ
    0.13
    赤
    0.13
    Act Density 0.044%

    No Known Activations