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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant increases or changes in numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.57
     مُعرِّف
    -0.54
     CURIAM
    -0.50
     vapormax
    -0.49
    nice
    -0.49
    Detail
    -0.47
    debe
    -0.47
    ToPoint
    -0.47
     Loose
    -0.47
     bParam
    -0.46
    POSITIVE LOGITS
     drastically
    1.24
     increase
    1.22
     dramatically
    1.18
     increased
    1.08
     substantially
    1.05
     significantly
    1.02
     increases
    1.01
     Increase
    0.99
    increase
    0.98
     decrease
    0.98
    Act Density 0.352%

    No Known Activations