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

    Neuronpedia

    INDEX
    Explanations

    action words related to giving advice or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to giving advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á
    -0.69
    ccording
    -0.65
    ר
    -0.63
    Dub
    -0.62
    ateral
    -0.62
    aband
    -0.61
    ãĥ´ãĤ¡
    -0.60
    egal
    -0.59
    à©
    -0.58
    à¨
    -0.58
    POSITIVE LOGITS
     us
    1.01
     him
    0.98
    ingly
    0.96
    tale
    0.88
     me
    0.84
     them
    0.79
    warn
    0.79
    ostics
    0.70
    orate
    0.69
    ments
    0.69
    Act Density 0.065%

    No Known Activations