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

    Neuronpedia

    INDEX
    Explanations

    documents that include reports or official study findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.16
    anou
    -0.15
    perty
    -0.15
    vents
    -0.14
    618
    -0.14
    ibase
    -0.14
    ìĹĦ
    -0.14
    gil
    -0.14
    ITY
    -0.14
    är
    -0.14
    POSITIVE LOGITS
    edly
    0.28
    orial
    0.26
    able
    0.26
    ings
    0.24
     card
    0.23
     cards
    0.21
    ability
    0.20
    ers
    0.19
    age
    0.18
    card
    0.18
    Act Density 0.029%

    No Known Activations