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

    Neuronpedia

    INDEX
    Explanations

    words emphasizing the concept of absoluteness or lack of relativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -0.85
     itſelf
    -0.80
     Formosa
    -0.77
     photolibrary
    -0.75
     Reſ
    -0.75
    complexContent
    -0.73
     Monfieur
    -0.73
     ―――――
    -0.72
    دانشنامهٔ
    -0.72
     Anſ
    -0.72
    POSITIVE LOGITS
     rel
    0.98
     relative
    0.92
    rel
    0.89
    Relative
    0.82
     absolute
    0.82
    relative
    0.82
     Relative
    0.80
     RELATIVE
    0.78
    RELATIVE
    0.77
    Rel
    0.71
    Act Density 0.136%

    No Known Activations