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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.14
    DeleteBehavior
    -1.03
    SharedDtor
    -0.92
    IVEREF
    -0.91
    انيف
    -0.85
    Rohy
    -0.84
     pinulongan
    -0.83
     $_"
    -0.82
    ValueGeneration
    -0.81
     Phosphate
    -0.78
    POSITIVE LOGITS
    <bos>
    0.62
    .
    0.51
    ,
    0.47
     (
    0.47
     with
    0.46
    ↵
    0.46
     {
    0.42
    1
    0.41
    I
    0.41
     still
    0.40
    Act Density 0.029%

    No Known Activations