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

    Neuronpedia

    INDEX
    Explanations

    code structure elements related to variable declarations and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sodom
    -0.56
    IBinder
    -0.54
     mast
    -0.54
     Maced
    -0.53
    ও
    -0.52
     Ptole
    -0.52
     demurrer
    -0.50
     Agamemnon
    -0.49
     Martine
    -0.49
     cargoes
    -0.49
    POSITIVE LOGITS
    WillAppear
    0.72
     فريبيس
    0.69
     etc
    0.67
    !*\
    0.66
    //
    0.64
    dafx
    0.62
     kasarigan
    0.62
    帖最后由
    0.62
    ]();
    0.62
    NOPQRST
    0.60
    Act Density 0.218%

    No Known Activations