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

    Neuronpedia

    INDEX
    Explanations

    terms related to firmness and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.17
    oning
    -0.17
    othermal
    -0.17
    raman
    -0.15
    empo
    -0.15
    emp
    -0.15
    ric
    -0.15
    htub
    -0.14
    ract
    -0.14
    iating
    -0.14
    POSITIVE LOGITS
    ament
    0.36
    wares
    0.24
    aments
    0.23
    amental
    0.22
    idable
    0.21
    ness
    0.20
    iliar
    0.19
    AMENT
    0.19
    yard
    0.18
    ground
    0.18
    Act Density 0.013%

    No Known Activations