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

    Neuronpedia

    INDEX
    Explanations

    physical interactions and gestures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.21
     solidar
    -0.95
     protokol
    -0.92
     kooper
    -0.91
     embra
    -0.90
     ekos
    -0.90
     makro
    -0.89
    /***
    -0.89
     ert
    -0.88
     intersper
    -0.88
    POSITIVE LOGITS
     capitaine
    0.72
     alliés
    0.71
     demselben
    0.69
     vété
    0.68
     immerhin
    0.68
     mân
    0.66
     lecteur
    0.66
     docteur
    0.65
     seuil
    0.65
     gardien
    0.65
    Act Density 0.210%

    No Known Activations