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

    Neuronpedia

    INDEX
    Explanations

    times of the day in text, particularly the time in hours and minutes followed by 'p.m.'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'm' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behav
    -0.74
     Toast
    -0.67
     Spice
    -0.64
     recre
    -0.63
     scratched
    -0.63
     perks
    -0.61
     Behavior
    -0.61
    tan
    -0.61
     Nebula
    -0.60
    avorite
    -0.60
    POSITIVE LOGITS
    obiles
    1.02
    endment
    0.97
     EDT
    0.97
    .,
    0.96
    ourning
    0.88
    iles
    0.87
    igr
    0.86
     EST
    0.85
    obil
    0.85
    ansion
    0.84
    Act Density 0.021%

    No Known Activations