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

    Neuronpedia

    INDEX
    Explanations

    different types and categories of food-related phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     Roskov
    -1.05
     مرئيه
    -1.05
     itſelf
    -1.03
     oprot
    -1.03
     Monfieur
    -1.02
     Theſe
    -1.01
     ་་
    -0.99
     Majefty
    -0.98
     Anſ
    -0.97
    POSITIVE LOGITS
     N
    0.65
     i
    0.63
     (
    0.62
     H
    0.61
     h
    0.57
     I
    0.55
     and
    0.55
     v
    0.54
     Barbier
    0.53
     or
    0.52
    Act Density 1.101%

    No Known Activations