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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word 'Plus' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posób
    -0.67
     Jérusalem
    -0.67
     acrylique
    -0.60
     métallique
    -0.60
    reter
    -0.59
    anair
    -0.57
    脚注の使い方
    -0.57
    bitField
    -0.56
     Vienne
    -0.56
     Australie
    -0.56
    POSITIVE LOGITS
    Plus
    3.46
     Plus
    3.43
    plus
    3.40
     plus
    3.38
     PLUS
    3.15
    PLUS
    3.05
     плюс
    2.17
    minus
    1.80
    Minus
    1.73
     minus
    1.73
    Act Density 0.067%

    No Known Activations