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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -regexp
    -0.18
    Å¡ka
    -0.17
    ksen
    -0.17
    ahoo
    -0.17
    ês
    -0.16
    uckles
    -0.15
    kest
    -0.15
    ìĽĮíģ¬
    -0.15
    upo
    -0.14
    ummings
    -0.14
    POSITIVE LOGITS
    ible
    0.15
    {{{
    0.14
     Mech
    0.14
     Clo
    0.14
    件äºĭ
    0.13
    undy
    0.13
     Along
    0.13
     Oh
    0.13
     Of
    0.13
     Speaking
    0.13
    Act Density 0.018%

    No Known Activations