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

    Neuronpedia

    INDEX
    Explanations

    specific dates and times

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating time references or start times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    namese
    -0.71
    osponsors
    -0.70
    abled
    -0.70
    ken
    -0.66
    oft
    -0.66
    kept
    -0.65
    phies
    -0.64
    afia
    -0.64
    spread
    -0.63
    buster
    -0.60
    POSITIVE LOGITS
     earnest
    0.92
    here
    0.82
     dusk
    0.74
    morrow
    0.74
     anew
    0.68
     mids
    0.67
     2100
    0.67
     takeoff
    0.65
     sunrise
    0.65
     kindergarten
    0.63
    Act Density 0.146%

    No Known Activations