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

    Neuronpedia

    INDEX
    Explanations

    affirmations and agreements in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stoll
    -0.71
     Zav
    -0.68
    Mab
    -0.68
    Datuak
    -0.67
     ,
    -0.67
     Chor
    -0.67
     chocolates
    -0.66
     ASF
    -0.66
    Esther
    -0.65
     TOC
    -0.64
    POSITIVE LOGITS
     Yeah
    1.09
    Yeah
    1.08
    guys
    1.04
     GUYS
    1.03
     guys
    1.01
     yeah
    0.98
    Guys
    0.98
     guy
    0.96
     YEAH
    0.95
     Guys
    0.93
    Act Density 0.063%

    No Known Activations