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

    Neuronpedia

    INDEX
    Explanations

    contractions of 'is' in informal text

    oai_token-act-pair · gpt-3.5-turbo

    negations or forms of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.95
     newcom
    -0.92
    aditional
    -0.91
     pione
    -0.89
    Þ
    -0.89
     practition
    -0.89
     enthusi
    -0.88
     exting
    -0.87
    ò
    -0.87
    ß
    -0.86
    POSITIVE LOGITS
    't
    1.48
    ´
    0.85
    utm
    0.78
    �
    0.75
    \'
    0.74
    ÃŃ
    0.74
    nea
    0.74
    Dispatch
    0.73
    uts
    0.70
    iting
    0.69
    Act Density 0.089%

    No Known Activations