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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks signaling emotional or significant statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     here
    -0.15
    ÑģÑĤав
    -0.14
    orus
    -0.14
     himself
    -0.14
    _sets
    -0.14
    untime
    -0.14
     yourselves
    -0.14
    719
    -0.13
     ÙĨب
    -0.13
     Sets
    -0.13
    POSITIVE LOGITS
     Humph
    0.19
     however
    0.19
    ãĢĮâĢ¦âĢ¦
    0.17
     ......
    0.17
    Ngh
    0.17
     moreover
    0.16
     "...
    0.16
     “âĢ¦
    0.16
    ngo
    0.16
     original
    0.16
    Act Density 0.030%

    No Known Activations