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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.28
    1:0.14
    2:0.05
    3:0.05
    4:0.02
    5:0.04
    6:0.03
    7:0.01
    8:0.05
    9:0.05
    10:0.05
    11:0.16
    Negative Logits
    ocate
    -1.54
    etheless
    -1.54
    akespe
    -1.53
    版
    -1.52
    usional
    -1.52
     TAG
    -1.52
    cius
    -1.45
    ospace
    -1.45
    ocating
    -1.45
    OTS
    -1.44
    POSITIVE LOGITS
     1977
    1.62
     1993
    1.61
     Jr
    1.53
     1996
    1.52
     1992
    1.51
     1997
    1.51
     1998
    1.49
     1991
    1.49
    alli
    1.48
     1972
    1.47
    Act Density 0.002%

    No Known Activations