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

    Neuronpedia

    INDEX
    Explanations

    sentences punctuated with colons and their structural significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ako
    -0.14
    achuset
    -0.14
    aco
    -0.14
    ummy
    -0.14
    person
    -0.14
    YA
    -0.14
    uve
    -0.14
    िà¤ķत
    -0.13
    ön
    -0.13
    £
    -0.13
    POSITIVE LOGITS
    /UI
    0.14
     Halk
    0.14
    reesome
    0.14
    /Branch
    0.13
    acher
    0.13
    oux
    0.13
    hes
    0.13
    iet
    0.13
    HF
    0.13
     Lesser
    0.13
    Act Density 0.044%

    No Known Activations