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

    Neuronpedia

    INDEX
    Explanations

    variable assignments in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neſs
    -0.64
    InitStruct
    -0.60
    ness
    -0.59
     Hoy
    -0.58
    ound
    -0.57
    我还是
    -0.57
    ess
    -0.56
     doubtnut
    -0.56
     ustedes
    -0.56
    leſs
    -0.56
    POSITIVE LOGITS
     =
    1.80
    >=</
    1.69
    /=
    1.55
    }=
    1.33
     $=
    1.32
    )=
    1.30
    ]=
    1.28
     :=
    1.26
     $=\
    1.25
    _=
    1.23
    Act Density 0.180%

    No Known Activations