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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate an addition or positive emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dene
    -0.72
     Sark
    -0.71
    entery
    -0.69
    '},
    -0.69
    JAL
    -0.69
     initComponents
    -0.67
    Ars
    -0.66
     Jara
    -0.66
     Saty
    -0.65
    )("
    -0.64
    POSITIVE LOGITS
     PLUS
    1.44
    plus
    1.44
    PLUS
    1.38
     plus
    1.36
    Plus
    1.34
     Plus
    1.30
    mybatisplus
    1.21
     Minus
    1.13
    Minus
    1.05
    minus
    1.00
    Act Density 0.061%

    No Known Activations