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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to morality and ethical implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    637
    -0.15
    ÙĤÛĮ
    -0.15
     Wy
    -0.15
    Wy
    -0.14
     Burnett
    -0.14
    -validate
    -0.14
    awy
    -0.13
    łĢ
    -0.13
    -avatar
    -0.13
    spe
    -0.13
    POSITIVE LOGITS
     term
    0.22
     description
    0.20
     apt
    0.19
     word
    0.18
    -description
    0.18
    term
    0.17
    description
    0.17
     Term
    0.17
     adjective
    0.16
    word
    0.16
    Act Density 0.075%

    No Known Activations