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

    Neuronpedia

    INDEX
    Explanations

    mentions of sponsors or sponsorship

    oai_token-act-pair · gpt-3.5-turbo

    references to sponsorships or sponsors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shant
    -0.83
    empl
    -0.75
     Holmes
    -0.72
    ipt
    -0.70
    ilet
    -0.69
    ithe
    -0.68
     pend
    -0.67
    otom
    -0.66
     Volt
    -0.65
     Pav
    -0.65
    POSITIVE LOGITS
     sponsor
    1.44
     sponsors
    1.35
     sponsorship
    1.21
     sponsoring
    1.20
     sponsored
    1.13
     Spons
    1.09
    Spons
    1.03
    spons
    0.93
    sponsored
    0.86
    orship
    0.85
    Act Density 0.008%

    No Known Activations