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

    Neuronpedia

    INDEX
    Explanations

    words related to respect and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onta
    -0.17
    eliness
    -0.15
    ITY
    -0.15
    .extra
    -0.15
    ffective
    -0.14
    erals
    -0.14
    ondo
    -0.14
    erse
    -0.14
    icter
    -0.14
    icity
    -0.14
    POSITIVE LOGITS
    ably
    0.29
    ively
    0.21
    ible
    0.17
     muh
    0.17
    uously
    0.16
    uous
    0.16
    ibly
    0.15
    full
    0.15
    mund
    0.15
    chia
    0.15
    Act Density 0.034%

    No Known Activations