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

    Neuronpedia

    INDEX
    Explanations

    configuration parameters and options in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vechi
    -0.84
    berdayakan
    -0.73
    存于互联网档案馆
    -0.70
    lewati
    -0.68
     pioggia
    -0.68
    AxisAlignment
    -0.66
    bouncycastle
    -0.66
    ConstraintMaker
    -0.64
    SpringRunner
    -0.64
     varandra
    -0.64
    POSITIVE LOGITS
    andes
    0.64
     "
    0.57
    ('--
    0.55
    ATURA
    0.52
    AGAN
    0.52
     Op
    0.51
    IUrlHelper
    0.51
    seattle
    0.51
    Vtbl
    0.51
     note
    0.50
    Act Density 1.107%

    No Known Activations