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

    Neuronpedia

    INDEX
    Explanations

    descriptors indicating beauty or positive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.16
    -0.16
    iled
    -0.15
    oko
    -0.14
    -Based
    -0.14
    otropic
    -0.14
    ein
    -0.14
    عÙģ
    -0.14
    daq
    -0.13
    辺
    -0.13
    POSITIVE LOGITS
    lest
    0.22
    mente
    0.22
    -looking
    0.22
    -grand
    0.21
    oes
    0.19
    ous
    0.17
    ness
    0.17
    ment
    0.16
    ulously
    0.16
    emente
    0.15
    Act Density 0.062%

    No Known Activations