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

    Neuronpedia

    INDEX
    Explanations

    descriptors of characters' likability and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addir
    -0.18
    stral
    -0.16
    nave
    -0.16
    FC
    -0.16
    urat
    -0.15
    .hs
    -0.15
     div
    -0.14
    attendance
    -0.14
    psilon
    -0.14
    defgroup
    -0.14
    POSITIVE LOGITS
     McGregor
    0.17
    ioned
    0.16
     personality
    0.16
    ÑĢиз
    0.16
    ÏĨι
    0.15
    ãĥ¼ãĥij
    0.15
    æĨ
    0.15
     koc
    0.15
    æĺŃåĴĮ
    0.15
    berger
    0.14
    Act Density 0.277%

    No Known Activations