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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating emotional reactions or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æħ
    -0.16
    isko
    -0.15
    amus
    -0.15
    lund
    -0.15
    legg
    -0.14
    icum
    -0.14
    iesel
    -0.14
    unce
    -0.14
    ndl
    -0.14
    ynet
    -0.14
    POSITIVE LOGITS
    kah
    0.15
    ÂĿ
    0.15
    utow
    0.14
     reb
    0.14
     N
    0.13
     endings
    0.13
    i
    0.13
    s
    0.13
    дÑĢеÑģ
    0.13
    ed
    0.13
    Act Density 0.073%

    No Known Activations