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

    Neuronpedia

    INDEX
    Explanations

    terminology related to decision-making processes and types of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ини
    -0.16
    ystack
    -0.15
    acos
    -0.15
    Ìī
    -0.15
    км
    -0.14
    .increment
    -0.14
    ìĶ
    -0.14
    opup
    -0.14
    виÑĤ
    -0.14
    acs
    -0.14
    POSITIVE LOGITS
    «
    0.19
    sole
    0.17
    Ïħγ
    0.15
    stell
    0.14
     jug
    0.14
    ABCDEFG
    0.14
     Mobil
    0.14
     Dough
    0.13
    olia
    0.13
    icense
    0.13
    Act Density 0.057%

    No Known Activations