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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    μβρίου
    -0.59
     Zacks
    -0.54
    新浪
    -0.50
    gator
    -0.50
    mediately
    -0.50
    нибудь
    -0.49
    ")"
    -0.49
    kegiatan
    -0.49
    umpad
    -0.48
    võ
    -0.48
    POSITIVE LOGITS
     yes
    3.14
    yes
    2.60
     YES
    2.19
     Yes
    2.11
    YES
    2.07
    Yes
    2.00
     yeah
    1.87
     yep
    1.56
     yea
    1.41
     sì
    1.40
    Act Density 0.075%

    No Known Activations