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

    Neuronpedia

    INDEX
    Explanations

    instances of inspection and quality control in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     missing
    -0.53
     Defense
    -0.48
    lization
    -0.48
     natal
    -0.47
    putra
    -0.46
     paralyzed
    -0.46
     Honors
    -0.46
     perek
    -0.44
     recognizable
    -0.44
     defense
    -0.44
    POSITIVE LOGITS
    oredCriteria
    1.05
    parsedMessage
    0.88
    balleur
    0.82
     estekak
    0.81
     jScrollPane
    0.78
    AutoScaleMode
    0.77
     disambiguazione
    0.75
     Italijanski
    0.75
     ErrIntOverflow
    0.74
    InitVars
    0.74
    Act Density 0.025%

    No Known Activations