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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future timelines or expectations

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly those related to the future and upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.83
    isters
    -0.71
    ooth
    -0.68
    ioch
    -0.67
    oba
    -0.67
    @#&
    -0.67
    umbnails
    -0.66
    atural
    -0.65
    ectomy
    -0.64
    agall
    -0.63
    POSITIVE LOGITS
     foreseeable
    1.85
     future
    1.69
     coming
    1.42
     upcoming
    1.39
     next
    1.32
     near
    1.30
     meantime
    1.28
     forthcoming
    1.27
    near
    1.21
    future
    1.16
    Act Density 0.151%

    No Known Activations