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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to cruelty and inhumanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enu
    -0.17
     timid
    -0.15
    isible
    -0.14
     Trim
    -0.14
     modest
    -0.14
    790
    -0.14
    onu
    -0.14
    ksi
    -0.14
     Quiet
    -0.14
     innoc
    -0.14
    POSITIVE LOGITS
     cold
    0.45
    cold
    0.36
    Cold
    0.34
     mean
    0.34
     call
    0.33
     Cold
    0.33
     colder
    0.32
     indifference
    0.32
     indifferent
    0.32
     insensitive
    0.32
    Act Density 0.499%

    No Known Activations