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

    Neuronpedia

    INDEX
    Explanations

    terms related to hints, exotic types, and fan speeds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '
    -0.65
     
    -0.56
    /*
    -0.54
    ↵↵
    -0.50
     M
    -0.48
     L
    -0.46
     W
    -0.45
    /**
    -0.45
    <h2>
    -0.45
    l
    -0.45
    POSITIVE LOGITS
     myſelf
    1.22
     himſelf
    1.18
     pleaſure
    1.15
     themſelves
    1.13
     purpoſe
    1.10
     itſelf
    1.02
     greateſt
    1.01
     houſe
    1.01
     leſs
    1.00
     ſtate
    0.98
    Act Density 0.529%

    No Known Activations