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

    Neuronpedia

    INDEX
    Explanations

    concepts related to virtue and moral character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gili
    -0.17
    ź
    -0.16
    имÑĥ
    -0.15
     CMP
    -0.15
     å¯
    -0.14
    å¾Ħ
    -0.14
    adoo
    -0.14
    erness
    -0.14
    acters
    -0.14
    ÏĢει
    -0.13
    POSITIVE LOGITS
     kabil
    0.17
    fully
    0.16
    -null
    0.16
    edef
    0.15
    egl
    0.15
    avir
    0.14
    pets
    0.14
    758
    0.14
    218
    0.14
    ove
    0.14
    Act Density 0.003%

    No Known Activations