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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation related to statistics and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /**
    -0.63
     male
    -0.51
    LSB
    -0.51
    geord
    -0.48
    assertj
    -0.47
    $
    -0.45
    ://$
    -0.45
     Lance
    -0.45
     HIM
    -0.45
     gas
    -0.44
    POSITIVE LOGITS
     $\
    0.89
     فريبيس
    0.88
    }{$\
    0.84
     $_
    0.81
    fillType
    0.79
    principalColumn
    0.79
    ~$\
    0.74
    ($_
    0.74
    ".$_
    0.72
    exitRule
    0.69
    Act Density 2.459%

    No Known Activations