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

    Neuronpedia

    INDEX
    Explanations

    HTML comment tags indicating specific sections of a webpage

    oai_token-act-pair · gpt-3.5-turbo

    HTML comment tags and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igs
    -0.76
     MacDonald
    -0.69
     horm
    -0.68
     rodent
    -0.67
     lett
    -0.65
    ggy
    -0.64
    lambda
    -0.64
     Zup
    -0.64
     myster
    -0.62
     Beir
    -0.62
    POSITIVE LOGITS
     -->
    1.88
    -->
    0.85
     adrenaline
    0.74
    ãĤ¯
    0.71
    /-
    0.71
     instant
    0.70
    catentry
    0.65
     </
    0.64
    ->
    0.64
    Present
    0.63
    Act Density 0.042%

    No Known Activations