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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Causes
    -0.61
     ACTIONS
    -0.60
     Explan
    -0.59
     gib
    -0.58
     Poles
    -0.58
    hed
    -0.57
     VIDEOS
    -0.57
    imate
    -0.55
     Fib
    -0.55
    hes
    -0.55
    POSITIVE LOGITS
    -'
    0.88
     alongside
    0.85
     graduating
    0.77
    successfully
    0.73
     starring
    0.69
     earning
    0.69
     alone
    0.69
     unsuccessfully
    0.68
    alli
    0.66
     specializing
    0.65
    Act Density 0.195%

    No Known Activations