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

    Neuronpedia

    INDEX
    Explanations

    past events that have finally come to a resolution or completion

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating achievement or completion of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     varied
    -0.65
    conom
    -0.64
    Spread
    -0.64
     Slate
    -0.62
     multiplier
    -0.62
     fluct
    -0.61
     constantly
    -0.60
     disproportionately
    -0.59
     Thib
    -0.58
     Vine
    -0.57
    POSITIVE LOGITS
    ped
    0.71
     reunited
    0.71
    onso
    0.70
     relent
    0.69
     exoner
    0.66
     closure
    0.64
     reun
    0.64
    izable
    0.64
     reconciliation
    0.64
     finally
    0.63
    Act Density 0.144%

    No Known Activations