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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tti
    -0.13
    coli
    -0.13
    aus
    -0.13
    stÃŃ
    -0.13
    alle
    -0.13
     Splash
    -0.13
    ibri
    -0.13
    dong
    -0.13
     Sunshine
    -0.13
    .Compile
    -0.12
    POSITIVE LOGITS
    ä¼łå¥ĩ
    0.14
     διά
    0.14
    146
    0.14
    ubern
    0.14
    chez
    0.13
    lar
    0.13
    lez
    0.13
    sız
    0.13
    416
    0.13
    acle
    0.13
    Act Density 0.207%

    No Known Activations