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

    Neuronpedia

    INDEX
    Explanations

    related articles or content

    oai_token-act-pair · gpt-3.5-turbo

    references to related content or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itar
    -0.80
     charm
    -0.77
    ces
    -0.76
     nails
    -0.67
     muster
    -0.66
     breaths
    -0.66
     utter
    -0.66
    handedly
    -0.65
    emon
    -0.65
     strongh
    -0.65
    POSITIVE LOGITS
     Related
    4.19
    Related
    1.36
     related
    1.19
     Signed
    1.12
     REL
    1.11
     Sources
    1.09
    related
    1.09
    Associated
    1.08
     Categories
    1.07
     Associated
    1.04
    Act Density 0.018%

    No Known Activations