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

    Neuronpedia

    INDEX
    Explanations

    instances of decision-making in social settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.75
    #+#
    -0.72
    ########.
    -0.69
    __":
    -0.66
    存于互联网档案馆
    -0.66
    rungsseite
    -0.65
    :+:
    -0.63
    XmlAccessType
    -0.62
    SequentialGroup
    -0.61
     confronti
    -0.60
    POSITIVE LOGITS
     pet
    0.43
     robot
    0.38
     sports
    0.36
     pirate
    0.35
     cartoon
    0.35
     جام
    0.35
     zap
    0.35
    Smarty
    0.34
     ad
    0.34
     tan
    0.34
    Act Density 0.607%

    No Known Activations