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

    Neuronpedia

    INDEX
    Explanations

    terms related to keys and locking mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entitled
    -0.16
    ales
    -0.15
    tur
    -0.14
    jour
    -0.14
    ulfilled
    -0.14
    .osgi
    -0.13
    aru
    -0.13
    ul
    -0.13
    Aceptar
    -0.13
    ient
    -0.13
    POSITIVE LOGITS
    strup
    0.16
    cott
    0.16
    riott
    0.15
    erea
    0.15
     Broad
    0.15
    inkel
    0.15
    Compat
    0.14
    ebek
    0.14
    cot
    0.14
    SharedPtr
    0.14
    Act Density 0.019%

    No Known Activations