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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with special characters like quotes or symbols

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.81
     Dirt
    -0.70
     Lunch
    -0.70
     Tid
    -0.70
     radar
    -0.69
     RAD
    -0.66
     Golem
    -0.66
     scattering
    -0.66
     Sanctuary
    -0.64
     uranium
    -0.63
    POSITIVE LOGITS
    should
    0.96
    ¹
    0.92
    ı
    0.90
    say
    0.90
    º
    0.81
    could
    0.81
    ¼
    0.80
    oras
    0.80
    certain
    0.78
    ij
    0.77
    Act Density 0.354%

    No Known Activations