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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.16
     til
    -0.15
    ipes
    -0.15
    ipe
    -0.15
    esome
    -0.15
    arily
    -0.15
    айд
    -0.14
    asn
    -0.13
    егоÑĢ
    -0.13
    nik
    -0.13
    POSITIVE LOGITS
    -archive
    0.14
     Although
    0.14
     رب
    0.14
    rou
    0.14
    ToProps
    0.13
    tec
    0.13
     Abuse
    0.13
    achi
    0.13
     although
    0.13
     This
    0.13
    Act Density 0.015%

    No Known Activations