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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistics and measurement of rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.34
    1:0.05
    2:0.01
    3:0.09
    4:0.11
    5:0.11
    6:0.04
    7:0.02
    8:0.09
    9:0.07
    10:0.02
    11:0.01
    Negative Logits
     backdrop
    -1.76
     pretext
    -1.64
    ��
    -1.63
     opio
    -1.62
     playbook
    -1.59
     Tiff
    -1.58
     sensibilities
    -1.57
     shader
    -1.55
     antioxid
    -1.50
     organisers
    -1.49
    POSITIVE LOGITS
    thood
    2.25
    mentation
    2.01
    ization
    1.99
    brance
    1.98
    ification
    1.94
    ocaust
    1.94
    aturation
    1.92
    ynthesis
    1.83
    itiveness
    1.82
    idence
    1.81
    Act Density 0.006%

    No Known Activations