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

    Neuronpedia

    INDEX
    Explanations

    text between double dashes which is often used for citations or elaborations within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a pause or interruption in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipop
    -0.70
    ysis
    -0.68
    esan
    -0.68
    hou
    -0.68
    oshop
    -0.62
    rences
    -0.62
    eus
    -0.61
     lag
    -0.60
     cons
    -0.58
     butterflies
    -0.58
    POSITIVE LOGITS
    _-
    0.89
    avanaugh
    0.69
    yes
    0.68
    ITS
    0.68
    gpu
    0.66
    ->
    0.66
    sil
    0.65
    culosis
    0.64
    natureconservancy
    0.64
    âĸº
    0.63
    Act Density 0.058%

    No Known Activations