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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics and statistics related to performance evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    844
    -0.18
    ons
    -0.17
    842
    -0.16
    idan
    -0.15
    poon
    -0.15
    ERS
    -0.15
    Enlarge
    -0.14
    onth
    -0.14
    970
    -0.14
    urous
    -0.14
    POSITIVE LOGITS
     Ridley
    0.15
    auer
    0.14
    ryo
    0.14
     complet
    0.14
    ftime
    0.13
    aning
    0.13
    .bind
    0.13
    arrison
    0.13
    dealer
    0.13
    @Spring
    0.13
    Act Density 0.027%

    No Known Activations