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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated emotional or reflective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĬ¨çĶŁæĪIJ
    -0.15
     Higgins
    -0.15
    ines
    -0.15
    ÑĨип
    -0.14
     knull
    -0.14
     Herb
    -0.14
    initely
    -0.13
    idis
    -0.13
     Yug
    -0.13
    اسطة
    -0.13
    POSITIVE LOGITS
     crack
    0.18
    -mf
    0.16
     Sanctuary
    0.15
    acious
    0.14
     Crack
    0.14
    acey
    0.14
    COPY
    0.14
    667
    0.14
    zo
    0.14
    576
    0.14
    Act Density 0.017%

    No Known Activations