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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and personal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alamofire
    -0.72
    Revenir
    -0.71
     محفوظة
    -0.70
     ProtoMessage
    -0.70
     चीज़ों
    -0.68
     HttpNotFound
    -0.66
    ngdoc
    -0.64
     MatDialog
    -0.64
     فريبيس
    -0.62
    ALAM
    -0.61
    POSITIVE LOGITS
    I
    0.75
     guess
    0.54
    It
    0.54
    A
    0.53
    In
    0.52
    We
    0.51
     am
    0.51
     don
    0.50
     had
    0.50
     A
    0.49
    Act Density 0.240%

    No Known Activations