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

    Neuronpedia

    INDEX
    Explanations

    sequences that mention a repetitive action or event occurring over multiple years in succession

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a repeated occurrence or duration of an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atively
    -0.78
    istas
    -0.77
    ources
    -0.72
     Extras
    -0.67
    reon
    -0.66
    },{"
    -0.65
     opt
    -0.61
    IENT
    -0.61
    ometers
    -0.61
     laughs
    -0.60
    POSITIVE LOGITS
     row
    1.12
     fortnight
    0.88
     month
    0.86
     nutshell
    0.83
     decade
    0.82
     week
    0.80
     millennium
    0.79
     calendar
    0.77
     bunch
    0.77
     quarter
    0.76
    Act Density 0.113%

    No Known Activations