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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.16
    vise
    -0.14
    ÙĪÛĮÙĨ
    -0.14
     circum
    -0.13
     tubes
    -0.13
    .memo
    -0.13
    Evaluator
    -0.13
    isy
    -0.13
     Tube
    -0.13
     notably
    -0.13
    POSITIVE LOGITS
    aran
    0.15
    219
    0.15
    angel
    0.14
    ackbar
    0.14
    py
    0.14
     Leah
    0.14
    (interface
    0.13
    ensch
    0.13
    iani
    0.13
    illos
    0.13
    Act Density 0.066%

    No Known Activations