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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing improvement and the quality of experiences or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullan
    -0.15
    olls
    -0.14
    azu
    -0.13
    tober
    -0.13
     closest
    -0.13
    igi
    -0.13
     NOT
    -0.13
    ident
    -0.13
     shortest
    -0.13
    cess
    -0.13
    POSITIVE LOGITS
     doubly
    0.44
     extra
    0.35
     cÃłng
    0.31
    -extra
    0.28
    even
    0.27
    extra
    0.26
     EVEN
    0.26
     ëįĶìļ±
    0.26
     EXTRA
    0.26
     even
    0.25
    Act Density 0.162%

    No Known Activations