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

    Neuronpedia

    INDEX
    Explanations

    references to attention and detail in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.18
    ped
    -0.17
    oce
    -0.17
    oca
    -0.16
    iales
    -0.15
    ãģ£
    -0.15
    odont
    -0.15
    ilers
    -0.15
    oner
    -0.15
    jour
    -0.15
    POSITIVE LOGITS
     span
    0.32
     spans
    0.30
     paid
    0.30
    al
    0.27
     Span
    0.26
    span
    0.26
    Span
    0.26
     Paid
    0.25
    -span
    0.25
    Paid
    0.23
    Act Density 0.016%

    No Known Activations