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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references in academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gins
    -0.19
     Garr
    -0.18
     Gong
    -0.17
     Garrison
    -0.16
     Graf
    -0.15
     Grades
    -0.15
     Gloss
    -0.15
     Gly
    -0.15
     Gas
    -0.15
    gram
    -0.14
    POSITIVE LOGITS
     Ge
    0.90
     ge
    0.87
    Ge
    0.84
    ge
    0.80
    _ge
    0.78
    .Ge
    0.70
    .ge
    0.69
     ге
    0.65
     geo
    0.63
     Ðĵе
    0.63
    Act Density 0.176%

    No Known Activations