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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "Yes" is present followed by additional information or confirmations

    oai_token-act-pair · gpt-3.5-turbo

    affirmative phrases or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģ«
    -0.78
    İĭ
    -0.78
    flows
    -0.77
    ements
    -0.77
    quarters
    -0.72
    rities
    -0.71
    que
    -0.70
    ool
    -0.70
    ULAR
    -0.69
    ement
    -0.69
    POSITIVE LOGITS
     yes
    0.83
     sir
    0.73
     Woo
    0.71
     thank
    0.70
     Anders
    0.67
    ymm
    0.61
     irrespective
    0.60
     although
    0.60
     Mistress
    0.60
     YES
    0.59
    Act Density 0.081%

    No Known Activations