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

    Neuronpedia

    INDEX
    Explanations

    titles and references related to art, criticism, and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bank
    -0.56
    ,
    -0.56
     hal
    -0.56
     ban
    -0.54
     bien
    -0.54
     ten
    -0.54
     or
    -0.54
     pu
    -0.52
     some
    -0.51
     four
    -0.50
    POSITIVE LOGITS
    ſelf
    1.23
    ſelves
    1.22
     Jefus
    1.22
     Majefty
    1.22
     Monfieur
    1.19
     itſelf
    1.16
     myſelf
    1.16
    tvguidetime
    1.13
     Shakspeare
    1.12
     Efq
    1.09
    Act Density 0.887%

    No Known Activations