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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidelines or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.55
    AddField
    -0.51
    CreateModel
    -0.51
    dite
    -0.51
    <bos>
    -0.49
    jsonPath
    -0.49
    =#{
    -0.48
    Más
    -0.48
    )))));
    -0.48
     Bath
    -0.48
    POSITIVE LOGITS
    SBATCH
    0.80
     exactamente
    0.69
     المعيارى
    0.65
    exactly
    0.65
    évaluateur
    0.64
    Exactly
    0.64
     exactly
    0.64
    readystatechange
    0.62
     exactement
    0.62
    новништво
    0.61
    Act Density 0.507%

    No Known Activations