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

    Neuronpedia

    INDEX
    Explanations

    references to social norms and their impact on behavior and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.77
    \{\\
    -0.68
    __':
    -0.67
    flap
    -0.66
    awtextra
    -0.63
    rophoto
    -0.60
    __(/*!
    -0.59
    abestanden
    -0.58
     sintético
    -0.58
     TÉCNICA
    -0.58
    POSITIVE LOGITS
    kheim
    0.59
    lunda
    0.52
     norms
    0.51
    homonymie
    0.50
     society
    0.49
    Aceptar
    0.49
    #+#
    0.47
    RegressionTest
    0.47
     Reverso
    0.47
    ียม
    0.47
    Act Density 0.360%

    No Known Activations