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

    Neuronpedia

    INDEX
    Explanations

    references to hats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Integ
    -0.67
     Impossible
    -0.66
    uality
    -0.64
     MSM
    -0.60
    YA
    -0.59
    IVES
    -0.57
     Presence
    -0.57
    Documents
    -0.57
    houn
    -0.57
     CLS
    -0.56
    POSITIVE LOGITS
    chet
    1.60
    chery
    1.33
    glers
    1.18
    ches
    1.15
    pins
    0.95
    cher
    0.95
     brim
    0.93
    gers
    0.93
    che
    0.92
    emark
    0.91
    Act Density 0.071%

    No Known Activations