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

    Neuronpedia

    INDEX
    Explanations

    rankings and competitive placements in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ummer
    -0.17
    acht
    -0.16
    :disable
    -0.15
    Union
    -0.15
     Elem
    -0.15
    hoo
    -0.15
     Union
    -0.14
    ãĤĪ
    -0.14
    abee
    -0.14
    anj
    -0.14
    POSITIVE LOGITS
     second
    0.17
    .fx
    0.15
     third
    0.15
    .runners
    0.15
     among
    0.15
    èº
    0.15
    stantiate
    0.14
    ylko
    0.14
    _nth
    0.14
    hev
    0.14
    Act Density 0.069%

    No Known Activations