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

    Neuronpedia

    INDEX
    Explanations

    positive reviews and expressions of satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YS
    -0.15
    795
    -0.15
    697
    -0.14
    Bes
    -0.14
    etails
    -0.14
    bes
    -0.14
    UNE
    -0.14
    696
    -0.14
    917
    -0.13
     Kramer
    -0.13
    POSITIVE LOGITS
     enough
    0.15
    iant
    0.15
     indeed
    0.14
    angler
    0.14
     ê¸
    0.14
    sik
    0.14
    oud
    0.14
    ible
    0.13
    rey
    0.13
    idge
    0.13
    Act Density 0.039%

    No Known Activations