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

    Neuronpedia

    INDEX
    Explanations

    concepts related to limits and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.69
    ires
    -0.68
    ORTS
    -0.62
     acad
    -0.61
    rams
    -0.59
    ritis
    -0.59
     sqor
    -0.58
     ceilings
    -0.58
     guts
    -0.58
    RAW
    -0.58
    POSITIVE LOGITS
    number
    0.79
    how
    0.78
     reckoned
    0.71
     amount
    0.71
     how
    0.68
     Zup
    0.68
    ween
    0.66
    time
    0.64
    cture
    0.63
    oldown
    0.62
    Act Density 1.202%

    No Known Activations