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

    Neuronpedia

    INDEX
    Explanations

    expressions related to something being wrong or problematic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allet
    -0.15
    eps
    -0.14
     ca
    -0.14
     Ca
    -0.14
    IGN
    -0.14
    èĬ³
    -0.13
    ä¸įåŃĺåľ¨
    -0.13
     IGN
    -0.13
    uegos
    -0.13
    BR
    -0.13
    POSITIVE LOGITS
    Extern
    0.16
    kyt
    0.16
    oji
    0.15
    ATUS
    0.15
    orum
    0.14
    kode
    0.14
    rape
    0.14
    ipe
    0.14
    deaux
    0.13
    oding
    0.13
    Act Density 0.028%

    No Known Activations