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

    Neuronpedia

    INDEX
    Explanations

    commands and phrases related to verification or validation actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APN
    -0.68
    /−
    -0.65
    醐
    -0.64
     Gilmour
    -0.63
    FECT
    -0.60
    ğraf
    -0.58
    subpackage
    -0.58
    >>>>>>>>
    -0.57
    Slices
    -0.57
    ERe
    -0.57
    POSITIVE LOGITS
     CHECK
    1.64
     checkers
    1.49
    CHECK
    1.47
     Checks
    1.44
     checks
    1.39
     Checking
    1.36
     Check
    1.32
    checks
    1.32
     Checked
    1.29
     checked
    1.28
    Act Density 0.052%

    No Known Activations