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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "notable" or related terms referring to significant features or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ỡ
    -0.18
    odes
    -0.14
    icari
    -0.14
    à¸ģลาà¸ĩ
    -0.14
    aya
    -0.14
    endale
    -0.14
     Scenes
    -0.14
    çľī
    -0.14
    úde
    -0.14
    alore
    -0.14
    POSITIVE LOGITS
    ably
    0.15
    opoulos
    0.15
    uba
    0.15
    FFE
    0.14
    olla
    0.14
    èĵ
    0.14
    ousse
    0.14
    eting
    0.13
    olk
    0.13
     civ
    0.13
    Act Density 0.008%

    No Known Activations