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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and expressions, particularly those involving personal pronouns and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.12
     greateſt
    -1.08
     ―――――
    -1.07
     Cæsar
    -1.07
     Anſ
    -1.06
     autorytatywna
    -1.03
     houſe
    -1.01
     Houſe
    -1.01
     raiſ
    -0.99
     Perſ
    -0.98
    POSITIVE LOGITS
     I
    0.83
     is
    0.76
     می
    0.72
     he
    0.70
     He
    0.68
     It
    0.68
     There
    0.68
     there
    0.64
     il
    0.63
     Tar
    0.62
    Act Density 0.026%

    No Known Activations