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

    Neuronpedia

    INDEX
    Explanations

    questions relating to location and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.15
     Roose
    -0.15
    desc
    -0.15
    CHAN
    -0.14
     Pax
    -0.14
    uet
    -0.14
    vg
    -0.14
    Desc
    -0.13
    loc
    -0.13
    ujet
    -0.13
    POSITIVE LOGITS
    IDX
    0.17
    RLF
    0.14
    æ¢
    0.14
    oleon
    0.14
    /swagger
    0.13
    afür
    0.13
    graf
    0.13
    olding
    0.13
     own
    0.13
    tık
    0.13
    Act Density 0.035%

    No Known Activations