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

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with "Su"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     juggling
    -0.71
     owl
    -0.64
     halves
    -0.62
    wright
    -0.62
     Blumenthal
    -0.62
     union
    -0.60
     AE
    -0.58
     Fired
    -0.57
     directions
    -0.56
     unions
    -0.56
    POSITIVE LOGITS
    icides
    1.38
    icide
    1.35
    icidal
    1.34
    zanne
    1.31
    arez
    1.20
    itable
    1.17
    cc
    1.09
    pper
    1.09
    zy
    1.06
    ited
    1.05
    Act Density 0.016%

    No Known Activations