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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.17
    ร
    -0.16
    e
    -0.15
    jas
    -0.15
    edd
    -0.15
    alu
    -0.15
    Ùĩد
    -0.14
    ed
    -0.14
    ingly
    -0.14
    ocha
    -0.14
    POSITIVE LOGITS
    ÑĶм
    0.16
    ahn
    0.15
     Güven
    0.15
    bane
    0.15
    -span
    0.14
    ProgressHUD
    0.14
     Nullable
    0.14
     Barton
    0.13
    emu
    0.13
     ActionType
    0.13
    Act Density 0.024%

    No Known Activations