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

    Neuronpedia

    INDEX
    Explanations

    references to plugins or add-ons, particularly related to software applications

    oai_token-act-pair · gpt-3.5-turbo

    references to plugins and add-ons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.62
     FANTASY
    -0.60
     Palm
    -0.60
     Griffith
    -0.59
    ãĥ£
    -0.58
    ouston
    -0.58
     Northern
    -0.57
     hus
    -0.57
     Ri
    -0.57
     firsthand
    -0.56
    POSITIVE LOGITS
    ins
    1.05
    ons
    0.99
    on
    0.95
    enabled
    0.91
    backs
    0.89
    in
    0.88
    INS
    0.85
    mob
    0.85
    forward
    0.84
    ups
    0.84
    Act Density 0.034%

    No Known Activations