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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant statistics or estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plusplus
    -0.15
    olang
    -0.14
    ylene
    -0.14
    ä¸Ģæł·
    -0.14
    toolbox
    -0.13
     (%)
    -0.13
    Äįila
    -0.13
     Evet
    -0.13
    ẫ
    -0.13
    ptype
    -0.13
    POSITIVE LOGITS
     equ
    0.44
     represents
    0.30
     translate
    0.30
     represent
    0.30
     translates
    0.29
     figure
    0.28
     represented
    0.27
     translated
    0.27
     compares
    0.26
     works
    0.25
    Act Density 0.090%

    No Known Activations