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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain sentence endings that signify either emphasis or concluding thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oloj
    -0.17
    Æł
    -0.15
    važ
    -0.15
    UTTON
    -0.14
    mpar
    -0.13
    anga
    -0.13
    ANTE
    -0.13
    ante
    -0.13
    IVO
    -0.13
    ift
    -0.12
    POSITIVE LOGITS
    Anyway
    0.18
     Anyway
    0.17
     Loc
    0.14
    ëĺIJ
    0.14
    ãģ¾ãģŁ
    0.14
    ählen
    0.14
     nu
    0.14
     loc
    0.14
     ayrıca
    0.14
    theless
    0.14
    Act Density 0.535%

    No Known Activations