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

    Neuronpedia

    INDEX
    Explanations

    tilde symbols and their various usages in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aren
    -0.17
    ials
    -0.17
    oreal
    -0.17
    "default
    -0.16
    holder
    -0.16
    outs
    -0.15
    н
    -0.14
    ignal
    -0.14
    tie
    -0.14
    uring
    -0.14
    POSITIVE LOGITS
    chez
    0.18
    atrix
    0.16
    ç·Ĵ
    0.16
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.16
     vast
    0.16
    rys
    0.15
    inp
    0.15
    708
    0.15
    gun
    0.14
    gesi
    0.14
    Act Density 0.030%

    No Known Activations