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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to organizations and roles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pector
    -0.15
    ynchronously
    -0.14
    ÛĮتÛĮ
    -0.14
    ackbar
    -0.14
    ollen
    -0.14
    ober
    -0.14
    pons
    -0.14
    uÅŁ
    -0.14
    cea
    -0.13
    ppelin
    -0.13
    POSITIVE LOGITS
    irit
    0.16
    igne
    0.15
    rez
    0.14
    patible
    0.14
    rette
    0.14
    arf
    0.14
    aves
    0.13
    pipes
    0.13
     Haram
    0.13
    licos
    0.13
    Act Density 0.004%

    No Known Activations