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

    Neuronpedia

    INDEX
    Explanations

    social media sharing options

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     duplication
    -0.64
     modifying
    -0.63
     adapting
    -0.63
     designing
    -0.62
     encountering
    -0.62
     progressing
    -0.62
     deletion
    -0.62
     referencing
    -0.61
     turning
    -0.61
     attracting
    -0.61
    POSITIVE LOGITS
    ety
    0.67
    oway
    0.61
    ector
    0.61
    arious
    0.61
    istar
    0.59
    cipled
    0.58
    dad
    0.58
    icts
    0.57
    emen
    0.57
    ixie
    0.57
    Act Density 0.703%

    No Known Activations