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

    Neuronpedia

    INDEX
    Explanations

    instances of control flow statements, particularly breaks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cona
    -0.19
    uitka
    -0.17
    ulan
    -0.15
    .CustomButton
    -0.15
    inka
    -0.15
    obot
    -0.15
    ertino
    -0.15
     Rei
    -0.15
    utdown
    -0.14
    upakan
    -0.14
    POSITIVE LOGITS
    orage
    0.15
     super
    0.15
     Sail
    0.14
     Mercer
    0.14
    0.14
    br
    0.14
     sw
    0.14
    201
    0.14
     lo
    0.14
     Boat
    0.14
    Act Density 0.005%

    No Known Activations