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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers with potential significance or patterns, particularly involving percentages and projective language

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data, particularly statistics or metrics related to performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     union
    -0.60
    atten
    -0.56
    ··
    -0.55
    >"
    -0.55
    hiba
    -0.54
    pill
    -0.53
     subst
    -0.53
    belt
    -0.52
     adjustment
    -0.52
    pen
    -0.50
    POSITIVE LOGITS
     Various
    0.68
    ortium
    0.67
     Tanks
    0.63
    à©
    0.63
     partName
    0.62
     Lastly
    0.62
    recated
    0.59
    VERTISEMENT
    0.59
     Orche
    0.59
     Cosponsors
    0.58
    Act Density 0.330%

    No Known Activations