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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and implications in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heim
    -0.64
    stor
    -0.63
    dis
    -0.63
     Atem
    -0.62
    ations
    -0.62
     fram
    -0.61
     Schild
    -0.61
    юрпри
    -0.60
    esk
    -0.60
    ning
    -0.60
    POSITIVE LOGITS
     =>
    1.45
    )=>
    1.26
    =>
    1.25
    (()=>
    1.16
    "=>
    1.15
     ()=>
    1.11
    ={()=>
    1.01
     ⇒
    0.97
    '=>
    0.97
     =>
    0.96
    Act Density 0.029%

    No Known Activations