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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [+
    -0.15
    ussen
    -0.14
    erde
    -0.14
    "indices
    -0.14
     Brewer
    -0.14
     PR
    -0.13
     resident
    -0.13
    “æĪij
    -0.13
    ylie
    -0.13
    unker
    -0.13
    POSITIVE LOGITS
    (S
    0.40
    (E
    0.40
    (H
    0.40
    (C
    0.39
    (M
    0.39
    (G
    0.39
    (B
    0.39
    (D
    0.39
    (A
    0.39
    (R
    0.39
    Act Density 0.155%

    No Known Activations