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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality or consequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.74
     scattering
    -0.72
     paternal
    -0.66
     stagger
    -0.64
     dirt
    -0.64
     prol
    -0.64
     eleph
    -0.64
     Annotations
    -0.64
     tremend
    -0.63
     cyan
    -0.63
    POSITIVE LOGITS
    ¹
    1.03
    £
    0.96
    º
    0.94
    ¢
    0.89
    ¡
    0.87
    Ī
    0.86
    ¬
    0.85
    į
    0.85
    ı
    0.84
    ¼
    0.84
    Act Density 0.762%

    No Known Activations