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

    Neuronpedia

    INDEX
    Explanations

    political and environmental terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or symbols that indicate emphasis or urgency in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.53
     scattering
    -0.51
     tremend
    -0.49
    creen
    -0.49
     Afric
    -0.47
     dispers
    -0.47
     guiActiveUnfocused
    -0.47
     shroud
    -0.46
     Annotations
    -0.46
     wide
    -0.45
    POSITIVE LOGITS
    ¡
    0.81
    ¹
    0.81
    ¬
    0.79
    º
    0.77
    ı
    0.75
    £
    0.74
    Ĵ
    0.73
    ¼
    0.73
    ł
    0.73
    ª
    0.73
    Act Density 0.512%

    No Known Activations