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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions and agreements that involve numerical or quantifiable aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onte
    -0.15
    owski
    -0.14
    aur
    -0.14
    forum
    -0.14
    phem
    -0.13
    rhs
    -0.13
    ski
    -0.13
     lett
    -0.13
    ighton
    -0.13
     åĽ½å®¶
    -0.13
    POSITIVE LOGITS
    agenta
    0.15
    ến
    0.15
     especially
    0.15
    zyst
    0.14
    кÑĢаÑĹ
    0.14
    ardon
    0.14
    874
    0.14
    dle
    0.13
     _______,
    0.13
     (),
    0.13
    Act Density 0.123%

    No Known Activations