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

    Neuronpedia

    INDEX
    Explanations

    affirmations and strong agreement expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oya
    -0.19
    rray
    -0.15
    occo
    -0.15
    å«
    -0.15
    enge
    -0.14
    lander
    -0.14
    OTOS
    -0.14
    oba
    -0.14
    /apis
    -0.13
    ayet
    -0.13
    POSITIVE LOGITS
     yes
    0.37
    yes
    0.34
     Yes
    0.30
     Yep
    0.28
    Yep
    0.25
    Yes
    0.25
     YES
    0.24
    =yes
    0.24
     Yup
    0.24
    .Yes
    0.23
    Act Density 0.084%

    No Known Activations