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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enhancing or improving something

    oai_token-act-pair · gpt-3.5-turbo

    the word "boost" and variations related to increasing or enhancing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.91
    rors
    -0.73
    bryce
    -0.71
    viol
    -0.69
    changes
    -0.69
     Lange
    -0.67
    sbm
    -0.66
    RIP
    -0.65
    Planet
    -0.64
    uka
    -0.64
    POSITIVE LOGITS
     morale
    0.95
     boost
    0.80
     productivity
    0.75
    ery
    0.73
     efficiency
    0.72
     boosting
    0.72
    ollen
    0.69
    tro
    0.69
     tide
    0.68
     adrenaline
    0.68
    Act Density 0.052%

    No Known Activations