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

    Neuronpedia

    INDEX
    Explanations

    phrases that categorize or classify groups or types of things

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.64
     =
    -0.53
    datab
    -0.52
     entrambi
    -0.51
     without
    -0.49
    dze
    -0.46
     confirmación
    -0.46
    mayın
    -0.46
    bit
    -0.44
     apresentar
    -0.44
    POSITIVE LOGITS
    "</
    0.81
    $.
    0.80
    ."</
    0.80
     hObject
    0.79
    WriteTagHelper
    0.75
    WriteAttribute
    0.75
     $_(
    0.74
    ](#
    0.73
    RefNanny
    0.72
    leſs
    0.72
    Act Density 0.012%

    No Known Activations