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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "wh"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blazers
    -0.70
     Duo
    -0.68
     BMC
    -0.66
     Sno
    -0.65
     mosaic
    -0.63
    WARE
    -0.63
     Grande
    -0.61
     liability
    -0.61
     styled
    -0.61
     clearance
    -0.61
    POSITIVE LOGITS
    ilst
    1.49
    istle
    1.39
    olly
    1.22
    olen
    1.17
    soever
    1.16
    ats
    1.15
    ipl
    1.14
    ole
    1.14
    ichever
    1.14
    irling
    1.13
    Act Density 0.004%

    No Known Activations