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

    Neuronpedia

    INDEX
    Explanations

    affirmations and expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oplay
    -0.16
    idot
    -0.15
    rchive
    -0.15
    .bz
    -0.15
    QRS
    -0.15
    eldorf
    -0.14
    945
    -0.13
    aña
    -0.13
    iders
    -0.13
    tec
    -0.13
    POSITIVE LOGITS
     yes
    0.45
     correct
    0.41
    yes
    0.40
     Yes
    0.36
     right
    0.34
     yup
    0.34
     Yep
    0.33
     Yup
    0.31
    Yep
    0.31
    Yes
    0.30
    Act Density 0.072%

    No Known Activations