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

    Neuronpedia

    INDEX
    Explanations

    numbers and their associated values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.85
     corrid
    -0.79
    mercial
    -0.75
     carbohyd
    -0.70
     reconc
    -0.67
    rongh
    -0.66
    efficients
    -0.66
     conclud
    -0.66
    ulet
    -0.66
    emade
    -0.66
    POSITIVE LOGITS
     Emin
    0.72
     Trance
    0.70
     Fury
    0.67
     Cascade
    0.65
     CentOS
    0.65
     Gutierrez
    0.65
     Reign
    0.65
     Chimera
    0.63
    Science
    0.59
     =================================================================
    0.59
    Act Density 0.023%

    No Known Activations