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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with special characters or symbols in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scatter
    -0.72
     condol
    -0.71
    anwhile
    -0.66
     scattering
    -0.65
     Mayo
    -0.65
     parity
    -0.64
     publishing
    -0.62
     guiActiveUnfocused
    -0.62
     Kenyan
    -0.62
     mutual
    -0.61
    POSITIVE LOGITS
    £
    0.98
    âĹ¼
    0.94
    ¹
    0.88
    ı
    0.85
    catentry
    0.84
    į
    0.81
    right
    0.79
    WER
    0.78
    Ī
    0.77
    Phill
    0.76
    Act Density 0.327%

    No Known Activations