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

    Neuronpedia

    INDEX
    Explanations

    references related to font types and styles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to types and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zimmer
    -0.69
     Yel
    -0.69
     Bots
    -0.67
    iae
    -0.66
     Morning
    -0.65
     Bills
    -0.65
     Rodrigo
    -0.63
     Wake
    -0.63
    aeper
    -0.61
     Kardash
    -0.61
    POSITIVE LOGITS
    face
    1.46
    faces
    1.39
    ahead
    1.23
    casting
    1.12
    etting
    1.04
    etter
    1.01
    cast
    0.95
    classes
    0.90
    alias
    0.86
     locality
    0.83
    Act Density 0.047%

    No Known Activations