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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dah
    -0.17
    876
    -0.17
    adle
    -0.16
    dera
    -0.15
    mah
    -0.15
    226
    -0.15
    alon
    -0.14
    ên
    -0.14
    mart
    -0.14
    Ùĭا
    -0.14
    POSITIVE LOGITS
    usz
    0.14
     Crush
    0.14
    fold
    0.14
    .notice
    0.14
     Arbor
    0.13
    .WinForms
    0.13
    ADM
    0.13
    orch
    0.13
     ellipt
    0.13
    uff
    0.13
    Act Density 0.096%

    No Known Activations