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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "man" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.63
     autos
    -0.61
    spot
    -0.59
    Indian
    -0.58
    EStream
    -0.58
     indo
    -0.57
     sacrific
    -0.57
    Italy
    -0.56
     pse
    -0.56
     IMAGES
    -0.55
    POSITIVE LOGITS
    ffe
    0.86
    arson
    0.75
    ciating
    0.74
    itely
    0.73
    aga
    0.72
    isse
    0.72
    schild
    0.68
    acion
    0.68
    emi
    0.68
    uve
    0.67
    Act Density 0.337%

    No Known Activations