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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling agreement or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of acknowledgment or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viol
    -0.69
    strings
    -0.64
    pec
    -0.61
    multiple
    -0.61
    sac
    -0.61
     brim
    -0.59
    pent
    -0.59
    string
    -0.59
    paralleled
    -0.58
    paralle
    -0.58
    POSITIVE LOGITS
    lahoma
    1.11
    AY
    1.04
     bye
    0.97
    Okay
    0.95
     alright
    0.95
     okay
    0.93
    Alright
    0.92
     yeah
    0.92
    yeah
    0.88
     fine
    0.85
    Act Density 0.027%

    No Known Activations