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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.88
     Normdatei
    -0.81
    ]")]
    -0.78
    SourceChecksum
    -0.77
    )$/,
    -0.75
    sidemargin
    -0.75
     useNavigate
    -0.74
    
    -0.74
     ModelExpression
    -0.74
    scrapy
    -0.74
    POSITIVE LOGITS
    त
    0.76
     statement
    0.56
    ত
    0.55
     jest
    0.55
    Auth
    0.55
    statement
    0.51
     Auth
    0.50
     stared
    0.49
    las
    0.48
     whether
    0.48
    Act Density 0.101%

    No Known Activations