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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and simplification cues

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.86
    TagHelper
    -0.81
    WriteAttribute
    -0.68
    PreferredItem
    -0.66
    AndEndTag
    -0.66
    */].
    -0.65
    ParallelGroup
    -0.64
    AnchorStyles
    -0.64
    ArgsConstructor
    -0.61
     defaultstate
    -0.61
    POSITIVE LOGITS
    mstyle
    0.60
     facilite
    0.57
    aarrggbb
    0.56
     Parke
    0.56
     دیکھیے
    0.55
     themſelves
    0.54
     الاطلاع
    0.54
    ⓘ
    0.53
    лера
    0.53
     informée
    0.53
    Act Density 0.221%

    No Known Activations