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

    Neuronpedia

    INDEX
    Explanations

    adjectives or nouns related to inherent qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to inherent traits, qualities, or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Europe
    -0.74
     Documents
    -0.72
    Streamer
    -0.70
    Talk
    -0.70
     newsletters
    -0.68
    ppa
    -0.67
    fare
    -0.65
    zon
    -0.65
     Tik
    -0.63
     Monteneg
    -0.62
    POSITIVE LOGITS
     inherent
    3.02
     innate
    2.24
     intrinsic
    2.09
    natural
    1.77
     implicit
    1.43
     latent
    1.42
     supernatural
    1.36
     inherently
    1.31
     divine
    1.21
     infinite
    1.20
    Act Density 0.042%

    No Known Activations