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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to questions of identity and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ual
    -0.15
    he
    -0.14
    enh
    -0.13
     Kirby
    -0.13
    542
    -0.13
    als
    -0.13
    her
    -0.13
    qual
    -0.13
    its
    -0.13
    zig
    -0.12
    POSITIVE LOGITS
    ’S
    0.22
    'S
    0.22
    artner
    0.17
    Ä°
    0.17
    ’T
    0.16
    ebo
    0.15
    ackle
    0.15
    ÐĿÐĺ
    0.14
    kiem
    0.14
    odash
    0.14
    Act Density 0.519%

    No Known Activations