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

    Neuronpedia

    INDEX
    Explanations

    scheduled events or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scheduled events or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abba
    -0.72
    rity
    -0.70
     Flavoring
    -0.68
    lean
    -0.64
    bert
    -0.63
    goo
    -0.63
    ds
    -0.61
    rets
    -0.59
    bour
    -0.59
    tein
    -0.59
    POSITIVE LOGITS
     Parenthood
    1.02
    uled
    0.87
     for
    0.85
     to
    0.77
     TBD
    0.77
     downtime
    0.72
    dule
    0.69
     maintenance
    0.67
     Mondays
    0.66
     premie
    0.64
    Act Density 0.045%

    No Known Activations