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

    Neuronpedia

    INDEX
    Explanations

    definitions and characteristics of specific terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheid
    -0.17
    zers
    -0.16
    bins
    -0.16
    itchens
    -0.15
    ebin
    -0.15
    phia
    -0.15
    eldorf
    -0.14
    Ñĥй
    -0.14
    ToSelector
    -0.14
    ammen
    -0.14
    POSITIVE LOGITS
     type
    0.19
     types
    0.19
     category
    0.17
    CATEGORY
    0.17
    们
    0.16
    åĢij
    0.16
    ãĤ¿ãĤ¤ãĥĹ
    0.15
    ç±»åŀĭ
    0.15
    subclass
    0.14
     Pacific
    0.14
    Act Density 0.299%

    No Known Activations