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

    Neuronpedia

    INDEX
    Explanations

    terms related to confirmation and affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    z
    -0.77
     י
    -0.67
     Syst
    -0.67
     y
    -0.65
     Gy
    -0.64
    ay
    -0.64
     Y
    -0.64
    ax
    -0.64
     Rok
    -0.63
    Rok
    -0.62
    POSITIVE LOGITS
     CONF
    1.32
    CONF
    1.21
     confirmations
    1.21
     Confirm
    1.17
     Conf
    1.15
     confessions
    1.12
    Conf
    1.10
     Confirmation
    1.09
     Conſ
    1.09
     Confe
    1.08
    Act Density 0.082%

    No Known Activations