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

    Neuronpedia

    INDEX
    Explanations

    specific sections or segments within a larger entity or composition

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions or parts of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akia
    -0.70
    oS
    -0.69
    igh
    -0.68
    terday
    -0.68
    udeau
    -0.68
    onda
    -0.64
     Flavoring
    -0.63
    yan
    -0.62
    paio
    -0.61
    outh
    -0.61
    POSITIVE LOGITS
     nearest
    0.92
     closest
    0.92
     furthe
    0.86
     whence
    0.79
     itself
    0.76
     mentioned
    0.75
    iverse
    0.74
    osphere
    0.74
     referred
    0.73
    same
    0.70
    Act Density 0.461%

    No Known Activations