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

    Neuronpedia

    INDEX
    Explanations

    words that convey uniqueness or exceptional qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.18
    uhn
    -0.18
    ourcem
    -0.16
    erman
    -0.15
    ender
    -0.14
    zend
    -0.14
    ãĥ¡ãĥ©
    -0.14
    chk
    -0.14
    isphere
    -0.14
    ory
    -0.14
    POSITIVE LOGITS
    ably
    0.18
    人çī©
    0.18
    ingly
    0.17
    -looking
    0.17
    ordinary
    0.16
    Ù
    0.16
    mente
    0.15
    ounce
    0.15
    ively
    0.14
    -grand
    0.14
    Act Density 0.044%

    No Known Activations