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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certainty and assertiveness

    oai_token-act-pair · gpt-3.5-turbo

    assertions or declarations about situations or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pegasus
    -0.79
     Rhodes
    -0.79
     Keynes
    -0.71
     Armageddon
    -0.67
     Liberty
    -0.66
     magistrate
    -0.65
     Excel
    -0.65
     Jerusalem
    -0.64
     Presbyter
    -0.64
     Newark
    -0.63
    POSITIVE LOGITS
    âĢ
    2.32
     âĢ
    1.77
    ãĢ
    1.56
    âľ
    1.45
    âĸ
    1.45
    âĢł
    1.39
    âĸł
    1.37
    âĹ
    1.35
    âĶ
    1.32
    ¨
    1.32
    Act Density 0.519%

    No Known Activations