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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'reference'

    oai_token-act-pair · gpt-4-turbo

    references to specific items, concepts, or people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awk
    -0.75
    ihad
    -0.74
    alach
    -0.70
    Ģ
    -0.69
    isine
    -0.66
    onew
    -0.66
    ailability
    -0.66
    ¯¯¯¯
    -0.65
    cffff
    -0.65
    omew
    -0.65
    POSITIVE LOGITS
     Reference
    0.94
    reference
    0.92
     reference
    0.83
     references
    0.83
    Reference
    0.77
    enza
    0.72
     Implementation
    0.70
    ogue
    0.69
    minist
    0.69
     References
    0.68
    Act Density 0.010%

    No Known Activations