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

    Neuronpedia

    INDEX
    Explanations

    references to citations or source identifiers in academic or research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.72
    tagHelperRunner
    -0.70
    hoeddwyd
    -0.69
    fjspx
    -0.68
    WriteBarrier
    -0.64
    otesi
    -0.60
    Rüyada
    -0.60
     msglen
    -0.60
    Архівовано
    -0.59
     Pim
    -0.59
    POSITIVE LOGITS
     linkovi
    0.55
    DialogComponent
    0.52
    aragua
    0.50
    uVar
    0.47
    页面存档备份
    0.47
    ftance
    0.47
    不及
    0.47
    prilis
    0.47
    queline
    0.44
     gonna
    0.44
    Act Density 0.030%

    No Known Activations