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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lower frequency or reduced amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.82
     BoxDecoration
    -0.79
    skosten
    -0.75
    bingen
    -0.73
     Kirkwood
    -0.72
     flip
    -0.69
     CarPlay
    -0.69
     Wib
    -0.69
     AssemblyTitle
    -0.69
    nemonic
    -0.69
    POSITIVE LOGITS
     less
    1.61
     Less
    1.53
     LESS
    1.53
    Less
    1.49
    less
    1.26
     Lessing
    1.18
    LESS
    1.15
     moins
    1.14
     menos
    1.11
     lefs
    1.07
    Act Density 0.082%

    No Known Activations