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

    Neuronpedia

    INDEX
    Explanations

    themes related to social justice and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.82
     Efq
    -0.80
     myſelf
    -0.80
     Monfieur
    -0.77
     Reſ
    -0.76
     himſelf
    -0.73
     Majefty
    -0.72
     perfons
    -0.71
     themſelves
    -0.70
     समीक्षाओं
    -0.68
    POSITIVE LOGITS
     social
    0.77
     moral
    0.64
     global
    0.61
     activism
    0.57
     environmental
    0.57
     ethical
    0.56
     Social
    0.56
     addressing
    0.56
     impact
    0.51
    0.51
    Act Density 0.464%

    No Known Activations