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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Toll
    -0.17
    venge
    -0.16
    elia
    -0.16
    eration
    -0.15
    chema
    -0.15
    vido
    -0.15
    vida
    -0.14
    ην
    -0.14
    yor
    -0.14
    ogne
    -0.13
    POSITIVE LOGITS
    rames
    0.20
    rame
    0.20
    unny
    0.19
    876
    0.19
    ield
    0.19
    rit
    0.18
    ecycle
    0.18
    ruit
    0.17
    æŀľ
    0.17
    _then
    0.17
    Act Density 0.090%

    No Known Activations