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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental or political actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "For" or indicate a rationale or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Finish
    -0.69
    uminati
    -0.68
    etsy
    -0.66
    enary
    -0.63
    foundland
    -0.63
     referral
    -0.62
    pez
    -0.61
    )",
    -0.61
    =-=-=-=-
    -0.60
     ðŁĻĤ
    -0.60
    POSITIVE LOGITS
    cknowled
    0.85
     meanwhile
    0.77
    neath
    0.72
     however
    0.69
     therefore
    0.69
    xtap
    0.68
    Such
    0.64
    ogether
    0.64
    sequently
    0.64
    cing
    0.64
    Act Density 0.458%

    No Known Activations