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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases that introduce reasoning or conclusions in formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.56
     ElementRef
    -0.53
     TextAppearance
    -0.52
     ...)
    -0.52
    ...',
    -0.51
    toolStripButton
    -0.51
    Autoritní
    -0.49
    ]="
    -0.48
     […]
    -0.47
    fread
    -0.47
    POSITIVE LOGITS
    <bos>
    0.97
     skydd
    0.68
     marquées
    0.68
     femininas
    0.68
     défauts
    0.64
     vicenda
    0.63
    ParallelGroup
    0.62
     deose
    0.61
     prêtres
    0.61
     dianteiro
    0.60
    Act Density 1.702%

    No Known Activations