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

    Neuronpedia

    INDEX
    Explanations

    assignments or declarations of types and values in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leſs
    -0.80
     doubtnut
    -0.77
    neſs
    -0.65
     itſelf
    -0.64
     ſever
    -0.62
     ſeveral
    -0.61
     typelib
    -0.60
    terness
    -0.59
     Theſe
    -0.58
     Heff
    -0.58
    POSITIVE LOGITS
     =
    2.01
    >=</
    1.37
    =
    1.31
     $=$
    1.24
    }=
    1.23
    )=
    1.21
     $=
    1.18
     :=
    1.18
    ]=
    1.13
    /=
    1.08
    Act Density 0.322%

    No Known Activations