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

    Neuronpedia

    INDEX
    Explanations

    the repeated phrase "as" indicating comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olini
    -0.17
    aira
    -0.16
    OLLOW
    -0.16
     EVT
    -0.15
    ↵↵
    -0.15
    engin
    -0.15
    ourage
    -0.15
    ugi
    -0.14
    ettle
    -0.14
    åįĵ
    -0.14
    POSITIVE LOGITS
     well
    0.84
    well
    0.79
     Well
    0.62
    Well
    0.60
     WELL
    0.57
     bien
    0.56
     wells
    0.46
     wel
    0.46
    wel
    0.44
    “Well
    0.36
    Act Density 0.026%

    No Known Activations