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

    Neuronpedia

    INDEX
    Explanations

    references to decades or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades or historical periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.69
    ahu
    -0.67
    aspx
    -0.66
    Quality
    -0.66
    OTE
    -0.65
    Choice
    -0.65
     snipp
    -0.64
    Primary
    -0.63
    SourceFile
    -0.63
     Removal
    -0.62
    POSITIVE LOGITS
     onwards
    0.82
     hindsight
    0.75
     onward
    0.74
     millennium
    0.74
    urches
    0.72
     nostalg
    0.71
     Scandinav
    0.70
     Algeria
    0.70
     era
    0.69
     vividly
    0.68
    Act Density 0.278%

    No Known Activations