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

    Neuronpedia

    INDEX
    Explanations

    instances of quantified amounts and representative groupings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yre
    -0.16
    одÑĭ
    -0.16
    ount
    -0.15
    izik
    -0.15
    ertz
    -0.15
    anje
    -0.15
     Erg
    -0.14
    QUENCE
    -0.14
    cly
    -0.13
    iste
    -0.13
    POSITIVE LOGITS
     each
    0.42
    each
    0.36
     każ
    0.34
     кажд
    0.33
     Each
    0.33
    Each
    0.33
     каждого
    0.32
    æ¯ı
    0.32
     every
    0.32
     EACH
    0.32
    Act Density 0.245%

    No Known Activations