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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant milestones or extremes in time or event

    oai_token-act-pair · gpt-3.5-turbo

    references to "all-time highs" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.83
    ropri
    -0.67
    eur
    -0.66
    iar
    -0.65
    endas
    -0.64
    yout
    -0.63
    »Ĵ
    -0.62
    ramid
    -0.61
    idav
    -0.61
    ectomy
    -0.60
    POSITIVE LOGITS
    theless
    0.74
    brates
    0.70
    days
    0.70
    consuming
    0.68
    brate
    0.68
    flies
    0.67
    birds
    0.67
     except
    0.67
     highs
    0.66
     ILCS
    0.66
    Act Density 0.027%

    No Known Activations