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

    Neuronpedia

    INDEX
    Explanations

    words related to giving praise

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.78
     Shooter
    -0.71
     Danger
    -0.66
     Caf
    -0.65
     Const
    -0.65
     Illegal
    -0.64
     Zimmerman
    -0.64
     intest
    -0.64
     sho
    -0.64
     Lent
    -0.63
    POSITIVE LOGITS
     bestowed
    0.96
    worthy
    0.93
    seekers
    0.85
    vation
    0.85
    giving
    0.83
     praises
    0.81
    hovah
    0.80
     accol
    0.80
     acclaim
    0.79
    animous
    0.79
    Act Density 0.061%

    No Known Activations