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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices or decisions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icc
    -0.76
    agate
    -0.74
    ORPG
    -0.73
    izon
    -0.73
    odes
    -0.70
    zing
    -0.69
    SourceFile
    -0.69
    adelphia
    -0.69
    nih
    -0.66
    ÅĤ
    -0.64
    POSITIVE LOGITS
     moreover
    1.05
     secondly
    1.04
     consequently
    1.03
     alas
    0.95
     therefore
    0.94
     furthermore
    0.91
     accordingly
    0.86
     importantly
    0.86
     frankly
    0.86
     unsurprisingly
    0.86
    Act Density 0.076%

    No Known Activations