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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and control

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating governance or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soon
    -0.81
    raq
    -0.79
    ache
    -0.78
    enery
    -0.77
    iate
    -0.75
    apest
    -0.74
    asy
    -0.74
    raise
    -0.73
    assi
    -0.72
    ased
    -0.72
    POSITIVE LOGITS
     virtue
    0.93
     fiat
    0.83
     vested
    0.77
     different
    0.76
     strict
    0.75
     proprietary
    0.70
     varying
    0.69
     mutual
    0.69
     imagination
    0.68
     hears
    0.68
    Act Density 0.122%

    No Known Activations