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

    Neuronpedia

    INDEX
    Explanations

    references or citations in a scholarly text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advis
    -0.72
     applicable
    -0.66
     dictatorship
    -0.64
     chopping
    -0.62
    glers
    -0.61
     stewards
    -0.61
     budgets
    -0.61
     leap
    -0.61
     rule
    -0.60
     roundup
    -0.60
    POSITIVE LOGITS
    J
    1.31
    E
    1.18
    A
    1.17
    Va
    1.16
    C
    1.14
    S
    1.13
    L
    1.12
    R
    1.11
    P
    1.11
    O
    1.10
    Act Density 0.049%

    No Known Activations