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

    Neuronpedia

    INDEX
    Explanations

    phrases that express authenticity and personal experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imli
    -0.14
    ..↵↵↵↵
    -0.14
    AndPassword
    -0.13
    ibri
    -0.13
    ëŀĺ
    -0.13
    éľŀ
    -0.13
    é¡
    -0.13
     onCancelled
    -0.12
    prung
    -0.12
    .newaxis
    -0.12
    POSITIVE LOGITS
    100
    0.77
     hundred
    0.65
     Hundred
    0.60
     completely
    0.52
    çĻ¾
    0.52
     totally
    0.47
     entirely
    0.44
     çĻ¾
    0.44
     Completely
    0.44
    å®Įåħ¨
    0.41
    Act Density 0.356%

    No Known Activations