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

    Neuronpedia

    INDEX
    Explanations

    the word "whereas" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Paz
    -0.73
     كومونز
    -0.70
    kone
    -0.66
     "
    -0.64
    .
    -0.64
     jed
    -0.63
    н
    -0.62
    o
    -0.61
     Patton
    -0.61
     to
    -0.60
    POSITIVE LOGITS
    parsedMessage
    1.39
    theless
    1.05
    DockStyle
    1.02
    PerformLayout
    1.00
     contextLoads
    0.99
    adays
    0.97
     Merri
    0.95
    rrggbb
    0.94
     doughnuts
    0.94
     huts
    0.93
    Act Density 0.010%

    No Known Activations