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

    Neuronpedia

    INDEX
    Explanations

    terms related to correctness and suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.82
    ViewFeatures
    -0.82
    enterOuterAlt
    -0.73
    ]){
    -0.68
     FormData
    -0.68
    principalColumn
    -0.67
    inigungs
    -0.66
    ]));
    -0.60
    setVerticalGroup
    -0.58
    ennie
    -0.58
    POSITIVE LOGITS
     appropriate
    1.11
     Appropriate
    0.90
    Appropriate
    0.90
     odpowied
    0.89
     enough
    0.87
    appropriate
    0.85
     adequate
    0.84
     appropriately
    0.84
     suitable
    0.80
     correct
    0.78
    Act Density 0.412%

    No Known Activations