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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal transformation or significant life changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agrico
    -0.56
    unsqueeze
    -0.52
     études
    -0.52
    ible
    -0.52
     vœux
    -0.50
    EndContext
    -0.49
     LIRE
    -0.48
    LookAnd
    -0.48
     समीक्षक
    -0.48
     xong
    -0.47
    POSITIVE LOGITS
    Hochspringen
    0.68
    quels
    0.65
    TagHelper
    0.60
    チコミ
    0.55
     мәкал
    0.54
     pylint
    0.53
    jspb
    0.52
     unexpectedly
    0.52
    تقاوى
    0.50
     confront
    0.50
    Act Density 0.227%

    No Known Activations