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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or developments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joined
    -0.80
    hari
    -0.78
    arella
    -0.73
    etsk
    -0.68
    astics
    -0.67
    eno
    -0.66
    arten
    -0.66
    pour
    -0.66
    ova
    -0.66
    linger
    -0.63
    POSITIVE LOGITS
     aforementioned
    1.10
     latter
    1.03
     entire
    0.95
     remainder
    0.84
     impending
    0.83
     same
    0.80
     dreaded
    0.79
     utmost
    0.79
     sexes
    0.79
     foregoing
    0.79
    Act Density 0.298%

    No Known Activations