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

    Neuronpedia

    INDEX
    Explanations

    specific items in a list or a sequence

    oai_token-act-pair · gpt-3.5-turbo

    colons followed by lists or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.70
    undai
    -0.68
     bars
    -0.66
     simulac
    -0.66
    ĸļ
    -0.65
     arena
    -0.64
    okane
    -0.63
     shooters
    -0.62
     tremend
    -0.62
     neighb
    -0.62
    POSITIVE LOGITS
     "âĢ¦
    0.83
     Firstly
    0.78
     âĹı
    0.76
     namely
    0.75
    hips
    0.73
    *)
    0.71
    1
    0.71
    husband
    0.70
    $$$$
    0.69
    *:
    0.69
    Act Density 0.084%

    No Known Activations