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

    Neuronpedia

    INDEX
    Explanations

    Lex-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ============
    -0.75
    ========
    -0.70
    CVE
    -0.68
    ¶ħ
    -0.66
    ONEY
    -0.63
     duly
    -0.63
     parties
    -0.63
     Tot
    -0.62
    aternity
    -0.61
    OST
    -0.61
    POSITIVE LOGITS
    ibility
    1.14
    ible
    1.03
    es
    0.98
    avier
    0.97
    ius
    0.92
    ibly
    0.92
    icon
    0.91
    lex
    0.89
    imus
    0.88
    icons
    0.88
    Act Density 0.010%

    No Known Activations