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

    Neuronpedia

    INDEX
    Explanations

    mentions of official organizations and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vertisement
    -0.17
    ake
    -0.17
    /she
    -0.15
    ãģĦãģĨ
    -0.15
    AKE
    -0.15
    -0.15
    uce
    -0.14
    .Btn
    -0.14
    аÑĢÑħ
    -0.14
     Tone
    -0.14
    POSITIVE LOGITS
    naire
    0.21
    aires
    0.20
    nal
    0.20
    edImage
    0.18
    ately
    0.17
    aire
    0.17
    naires
    0.17
    ors
    0.16
    ing
    0.16
     noqa
    0.16
    Act Density 0.029%

    No Known Activations