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

    Neuronpedia

    INDEX
    Explanations

    references to specific data formats or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.92
    e
    -0.82
    a
    -0.77
    ″]
    -0.66
     snippetHide
    -0.62
    t
    -0.60
    GraphicsUnit
    -0.59
    i
    -0.58
    eas
    -0.57
    ″
    -0.55
    POSITIVE LOGITS
     незавершена
    0.67
    UnsafeEnabled
    0.63
     varandra
    0.61
    7
    0.61
    8
    0.60
    9
    0.60
    5
    0.58
    6
    0.57
     Normdatei
    0.57
     bär
    0.56
    Act Density 0.223%

    No Known Activations