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

    Neuronpedia

    INDEX
    Explanations

    concepts related to viewpoints or interpretations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subjective interpretations and definitions of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.72
    orst
    -0.71
    vine
    -0.70
    fam
    -0.70
    reau
    -0.68
     depended
    -0.64
    stead
    -0.64
    ktop
    -0.63
    hement
    -0.63
    imentary
    -0.62
    POSITIVE LOGITS
     how
    0.82
     criminality
    0.81
     what
    0.79
     morality
    0.77
     reality
    0.73
     masculinity
    0.72
     sexuality
    0.72
     homosexuality
    0.70
     events
    0.70
     rationality
    0.70
    Act Density 0.171%

    No Known Activations