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

    Neuronpedia

    INDEX
    Explanations

    confidence and encouragement related to trying new things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.51
    WriteLiteral
    -0.47
    TagHelper
    -0.46
    ModelAttribute
    -0.43
     rechange
    -0.43
     BoxDecoration
    -0.42
     skú
    -0.42
     AppCompat
    -0.41
    ANTES
    -0.41
     sind
    -0.41
    POSITIVE LOGITS
    一定会
    0.83
     zult
    0.73
    OGND
    0.71
     Surely
    0.71
     surely
    0.68
    DockStyle
    0.67
    Surely
    0.66
     bestimmt
    0.65
     garantiert
    0.65
     tikra
    0.63
    Act Density 0.107%

    No Known Activations