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

    Neuronpedia

    INDEX
    Explanations

    words denoting certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    modal and auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.76
    ares
    -0.72
    cember
    -0.71
    hops
    -0.68
    iku
    -0.67
    eper
    -0.66
    VILLE
    -0.66
    haul
    -0.66
     stalls
    -0.65
    unin
    -0.65
    POSITIVE LOGITS
    doi
    0.67
     latter
    0.66
     Stein
    0.63
     Forensic
    0.61
    nt
    0.60
     Teresa
    0.59
    iosyncr
    0.59
     stricter
    0.58
     commentators
    0.58
    sei
    0.58
    Act Density 0.086%

    No Known Activations