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

    Neuronpedia

    INDEX
    Explanations

    fruit-related nouns and adjectives

    oai_token-act-pair · gpt-3.5-turbo

    references to music, flavors, and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢł
    -0.74
    ãĥ©ãĥ³
    -0.71
    ãĤ¿
    -0.66
    accompan
    -0.66
    âĹ¼
    -0.65
    å£
    -0.64
    éŃĶ
    -0.63
    æł
    -0.62
    áµ
    -0.60
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
     anymore
    1.45
     either
    1.42
     nor
    1.15
     whatsoever
    1.15
     slightest
    1.14
    yet
    1.12
    nor
    1.12
     anyway
    1.01
     :(
    1.00
     necessarily
    0.97
    Act Density 0.478%

    No Known Activations