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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce conditional or uncertain scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Millard
    -0.77
     NPs
    -0.72
     ldc
    -0.72
     Pittman
    -0.71
     Balik
    -0.70
    IGraphics
    -0.69
     lid
    -0.68
    blic
    -0.67
     Hayden
    -0.66
     Carden
    -0.66
    POSITIVE LOGITS
     WHETHER
    1.28
    whether
    1.17
     whether
    1.12
     Whether
    1.09
    Whether
    1.08
     '{@
    0.90
    WHE
    0.83
    whe
    0.78
    乎
    0.78
    RectangleBorder
    0.75
    Act Density 0.035%

    No Known Activations