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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.16
    onda
    -0.16
    shed
    -0.16
    ski
    -0.15
    sy
    -0.15
    ote
    -0.15
    aine
    -0.15
    voy
    -0.15
    ync
    -0.15
    ervices
    -0.15
    POSITIVE LOGITS
    -of
    0.23
    ing
    0.20
    horn
    0.18
    er
    0.18
    course
    0.17
    ials
    0.16
    red
    0.16
    most
    0.16
    lies
    0.15
    hf
    0.15
    Act Density 0.025%

    No Known Activations