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

    Neuronpedia

    INDEX
    Explanations

    phrases related to viewpoints or opinions on various topics, especially government and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to opinions and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.78
    odder
    -0.71
    aunder
    -0.70
    vine
    -0.69
    staking
    -0.68
    lov
    -0.67
    ĸļ
    -0.67
    daq
    -0.67
    arse
    -0.67
    breaker
    -0.65
    POSITIVE LOGITS
     homosexuality
    1.02
     sexuality
    0.91
     criminality
    0.86
     morality
    0.84
     masculinity
    0.83
     evolution
    0.80
     Christianity
    0.77
     affairs
    0.77
     whether
    0.76
     events
    0.75
    Act Density 0.206%

    No Known Activations