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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.16
    brook
    -0.15
     MAC
    -0.15
    lix
    -0.15
    åĵ¡
    -0.14
     mạch
    -0.14
    unker
    -0.14
    ãĥ³ãĥ
    -0.14
    zl
    -0.14
    acades
    -0.14
    POSITIVE LOGITS
     addCriterion
    0.17
    ãģĭãģĹ
    0.16
    fol
    0.15
     Bale
    0.14
    /tiny
    0.14
     oy
    0.14
     åı·
    0.14
     æĻ´
    0.14
     cih
    0.14
     bush
    0.14
    Act Density 0.041%

    No Known Activations