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

    Neuronpedia

    INDEX
    Explanations

    references to religious themes and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ä°Y
    -0.20
    /goto
    -0.15
    orno
    -0.15
    úa
    -0.15
    reau
    -0.15
    rell
    -0.15
    estroy
    -0.14
    (yy
    -0.14
    Å¡t
    -0.14
    _HAVE
    -0.14
    POSITIVE LOGITS
     Who
    0.37
     Which
    0.33
    Who
    0.33
     qui
    0.32
    Which
    0.30
    who
    0.29
     Whoever
    0.28
     who
    0.28
     Qui
    0.27
    which
    0.26
    Act Density 0.225%

    No Known Activations