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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or unfavorable evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.83
     wikipagina
    -0.79
    =$?
    -0.74
     HasFactory
    -0.71
     дописавши
    -0.69
    aarrggbb
    -0.68
     $_"
    -0.67
     OFDb
    -0.67
    IVEREF
    -0.66
     insegna
    -0.65
    POSITIVE LOGITS
    _
    0.59
    SequentialGroup
    0.55
    \_
    0.53
     _
    0.51
     Hildebrand
    0.51
    DockStyle
    0.49
     White
    0.49
    _{
    0.49
    原始内容存档于
    0.49
    _,
    0.48
    Act Density 0.153%

    No Known Activations