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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quality or assessing something in a positive manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ”),
    -0.80
    _"+
    -0.79
    :",
    -0.78
     Hansen
    -0.75
    oan
    -0.72
    ’:
    -0.72
    ”:
    -0.71
     conos
    -0.70
    oen
    -0.70
    {}",
    -0.69
    POSITIVE LOGITS
     aswell
    1.02
     nahilalakip
    0.88
     CreateTagHelper
    0.83
     simil
    0.82
    väl
    0.78
    sizeCache
    0.75
     Purg
    0.68
     cũng
    0.68
    extAlignment
    0.67
    parsedMessage
    0.66
    Act Density 0.073%

    No Known Activations