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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing roles, identities, and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.14
    æŁĦ
    -0.14
     material
    -0.14
    rana
    -0.14
     offsetof
    -0.14
    TRIES
    -0.14
    minent
    -0.13
     gang
    -0.13
    éłħ
    -0.13
    umn
    -0.13
    POSITIVE LOGITS
    atta
    0.19
    bler
    0.15
    avanaugh
    0.15
    indle
    0.14
    ICLE
    0.14
     Souls
    0.14
    ëĮĢíķĻ
    0.14
    飲
    0.14
    iphone
    0.13
    upe
    0.13
    Act Density 0.410%

    No Known Activations