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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or syntax markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onenumber
    -0.58
     expéri
    -0.57
    ACTERS
    -0.54
    ntomas
    -0.53
    riwal
    -0.53
     Blazers
    -0.52
    thèse
    -0.51
     expériment
    -0.51
    fertigt
    -0.49
     enthou
    -0.49
    POSITIVE LOGITS
    GEN
    1.29
    expandindo
    1.25
    awtextra
    1.17
     مشين
    1.13
    UseVisualStyle
    1.11
     GEN
    1.02
    gen
    0.95
    Gen
    0.89
    findpost
    0.86
    unknownFields
    0.85
    Act Density 0.011%

    No Known Activations