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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    polator
    -0.15
    artz
    -0.14
    innen
    -0.14
    umer
    -0.14
    raig
    -0.14
    à¸ł
    -0.13
    alam
    -0.13
    -License
    -0.13
    /wiki
    -0.13
    ancell
    -0.13
    POSITIVE LOGITS
     apart
    0.17
    arov
    0.15
    ourn
    0.15
    aje
    0.15
     hor
    0.14
    ÑĤеÑĢн
    0.14
     es
    0.14
     hy
    0.13
    stup
    0.13
     im
    0.13
    Act Density 0.124%

    No Known Activations