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

    Neuronpedia

    INDEX
    Explanations

    specific phrases mentioning "yes" followed by confirming statements

    oai_token-act-pair · gpt-3.5-turbo

    affirmative phrases or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ethyst
    -0.71
    arted
    -0.70
    rils
    -0.70
    rance
    -0.70
    patch
    -0.69
    enta
    -0.69
    İĭ
    -0.68
    rival
    -0.68
    gall
    -0.66
    liner
    -0.66
    POSITIVE LOGITS
     sir
    0.96
     yes
    0.78
     THERE
    0.67
     thank
    0.67
     technically
    0.66
     yeah
    0.64
     please
    0.64
    terday
    0.60
     Mistress
    0.59
     Woo
    0.59
    Act Density 0.042%

    No Known Activations