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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically parentheses and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ruk
    -0.16
    amam
    -0.15
     Represent
    -0.15
    enger
    -0.15
    _typeof
    -0.14
    aris
    -0.14
    eki
    -0.14
     Phillips
    -0.13
    oples
    -0.13
    AMI
    -0.13
    POSITIVE LOGITS
    ROID
    0.14
    orce
    0.14
    ima
    0.14
    جاÙĨ
    0.14
    acomment
    0.14
    ë¡Ģ
    0.13
    .infinity
    0.13
     Klopp
    0.13
    ÅĻet
    0.13
    UMB
    0.13
    Act Density 0.030%

    No Known Activations