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

    Neuronpedia

    INDEX
    Explanations

    references to binary data structures and their manipulation in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hentet
    -0.58
    رشف
    -0.55
     Normdatei
    -0.52
     turbul
    -0.45
     iNdEx
    -0.45
     kapture
    -0.45
     ſta
    -0.43
     bogotá
    -0.41
     étrangère
    -0.41
     jugement
    -0.41
    POSITIVE LOGITS
     far
    0.85
    far
    0.78
     FAR
    0.76
    FAR
    0.69
    Far
    0.65
     seated
    0.59
     Far
    0.59
     lie
    0.54
    makeText
    0.54
    bin
    0.53
    Act Density 0.283%

    No Known Activations