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

    Neuronpedia

    INDEX
    Explanations

    references to prevailing rules, laws, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Handlung
    -0.77
     يتيمه
    -0.75
    ">—
    -0.70
     mergeFrom
    -0.69
    VIAF
    -0.68
    :✨
    -0.66
    MLLoader
    -0.65
    ValueStyle
    -0.64
    addCriterion
    -0.64
    WriteAttribute
    -0.63
    POSITIVE LOGITS
     under
    1.38
    Under
    1.23
     Under
    1.20
    under
    1.15
     UNDER
    1.10
    UNDER
    0.96
     bajo
    0.96
     sous
    0.93
     sotto
    0.91
    neath
    0.89
    Act Density 0.195%

    No Known Activations