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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with "I know"

    oai_token-act-pair · gpt-3.5-turbo

    instances of self-awareness or acknowledgment of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.79
     pione
    -0.78
    onding
    -0.77
     exting
    -0.76
    orthy
    -0.75
    pmwiki
    -0.69
    ā
    -0.66
    ermanent
    -0.66
    þ
    -0.66
    Đ
    -0.66
    POSITIVE LOGITS
     firsthand
    1.18
     how
    1.02
     plenty
    0.98
     exactly
    0.94
     what
    0.93
     lots
    0.90
     anecd
    0.89
     why
    0.89
     many
    0.89
     alot
    0.85
    Act Density 0.057%

    No Known Activations