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

    Neuronpedia

    INDEX
    Explanations

    text related to news, statements, and government activities

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that describe different types of Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imaginary
    -0.56
    topia
    -0.55
     invis
    -0.55
    flake
    -0.55
    ¢
    -0.54
     prest
    -0.54
     ç¥ŀ
    -0.53
     naïve
    -0.53
     liv
    -0.53
    problem
    -0.51
    POSITIVE LOGITS
     spokeswoman
    0.92
     spokesman
    0.92
     spokesperson
    0.80
     said
    0.77
     sources
    0.74
     allege
    0.74
     alleges
    0.73
     apologised
    0.72
     declined
    0.72
     criticised
    0.71
    Act Density 1.102%

    No Known Activations