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

    Neuronpedia

    INDEX
    Explanations

    dialogue or conversational elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.63
     sucker
    -0.59
     freaked
    -0.59
    didSet
    -0.57
    urança
    -0.56
     suckers
    -0.56
     sneaky
    -0.56
     dude
    -0.55
    weird
    -0.55
    awsze
    -0.54
    POSITIVE LOGITS
     Mr
    0.85
     gentlemen
    0.80
     sir
    0.79
    Mr
    0.78
     senhor
    0.72
     Ms
    0.71
     Monsieur
    0.70
    为您
    0.69
    Sir
    0.67
     gentleman
    0.67
    Act Density 0.207%

    No Known Activations