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

    Neuronpedia

    INDEX
    Explanations

    references to abstract concepts or undefined ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.87
    Portail
    -0.75
    xase
    -0.73
     Exile
    -0.69
    letzt
    -0.66
    prefixer
    -0.66
    anmoins
    -0.66
     poichè
    -0.66
    日閲覧
    -0.65
     ExecuteAsync
    -0.65
    POSITIVE LOGITS
     something
    2.98
    something
    2.81
    Something
    2.64
     Something
    2.61
     SOMETHING
    2.39
     somethin
    2.15
     anything
    1.93
    anything
    1.84
     qualcosa
    1.79
    Anything
    1.74
    Act Density 0.090%

    No Known Activations