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

    Neuronpedia

    INDEX
    Explanations

    affirmations or agreements in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morin
    -0.63
     MAS
    -0.62
     Amis
    -0.61
    yns
    -0.59
     ASC
    -0.59
    :///
    -0.56
     ATS
    -0.56
    atre
    -0.56
    ルの
    -0.55
     TOS
    -0.55
    POSITIVE LOGITS
    Yeah
    1.70
     Yeah
    1.68
     YEAH
    1.66
     yeah
    1.60
    YEAH
    1.51
    yeah
    1.50
     Yea
    1.08
    Yea
    1.06
    Nah
    1.01
    eah
    1.00
    Act Density 0.031%

    No Known Activations