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

    Neuronpedia

    INDEX
    Explanations

    references to schools and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leans
    -0.72
    ACTED
    -0.65
    OPLE
    -0.65
     heel
    -0.64
     Bots
    -0.62
    ioxide
    -0.61
    neum
    -0.60
     tame
    -0.59
     Ware
    -0.59
    aceae
    -0.58
    POSITIVE LOGITS
    girls
    1.46
    children
    1.39
    girl
    1.24
    kids
    1.19
    boy
    1.16
    boys
    1.14
    master
    1.02
    child
    1.01
    house
    1.00
    masters
    1.00
    Act Density 0.038%

    No Known Activations