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

    Neuronpedia

    INDEX
    Explanations

    expressions related to comparisons and statistics involving averages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.55
    haviour
    -0.52
    ležit
    -0.49
     desaparecido
    -0.47
    енча
    -0.46
     HasFactory
    -0.46
    TintMode
    -0.45
     eventdata
    -0.44
    łaszcza
    -0.43
    EndInit
    -0.43
    POSITIVE LOGITS
     approximate
    0.74
     projected
    0.73
     estimated
    0.72
    suggested
    0.70
    expected
    0.69
     suggested
    0.69
     number
    0.68
     expected
    0.68
    Approximate
    0.66
     starting
    0.64
    Act Density 0.458%

    No Known Activations