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

    Neuronpedia

    INDEX
    Explanations

    expressions of inquiry and uncertainty regarding situations or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    everything
    -0.68
     everything
    -0.67
     EVERYTHING
    -0.66
     ***!
    -0.66
    Everything
    -0.63
    NOTHING
    -0.61
     Everything
    -0.60
    
    -0.57
    nothing
    -0.56
     NOTHING
    -0.55
    POSITIVE LOGITS
     might
    1.17
     may
    1.09
    might
    0.91
    Might
    0.85
     Might
    0.84
     évent
    0.76
    may
    0.74
     måtte
    0.72
     vielleicht
    0.71
    sizeCache
    0.71
    Act Density 0.229%

    No Known Activations