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

    Neuronpedia

    INDEX
    Explanations

    references to fixed structures, values, or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hole
    -0.15
    aso
    -0.15
    thag
    -0.14
     bloss
    -0.14
    ÑĢаÑĩ
    -0.14
    ıda
    -0.14
     Meer
    -0.13
    htable
    -0.13
    /comment
    -0.13
    hest
    -0.13
    POSITIVE LOGITS
    -fixed
    0.19
     fixed
    0.16
     cá»ij
    0.16
     cứng
    0.16
    غاÙĦ
    0.15
    Fixed
    0.15
    _fixed
    0.15
    zie
    0.14
    936
    0.14
    fixed
    0.14
    Act Density 0.050%

    No Known Activations