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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beliefs, opinions, and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to belief and social actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    iven
    -0.68
    %.
    -0.67
    '.
    -0.67
    kson
    -0.63
    hyde
    -0.61
    zik
    -0.59
     '.
    -0.58
    AKING
    -0.57
    nown
    -0.57
    POSITIVE LOGITS
    pires
    0.79
     weren
    0.74
     aren
    0.73
     were
    0.70
    leground
    0.67
     are
    0.65
    hran
    0.65
    estern
    0.65
    alg
    0.60
    erate
    0.60
    Act Density 0.339%

    No Known Activations