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

    Neuronpedia

    INDEX
    Explanations

    words related to critical acclaim and performance metrics in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prite
    -0.14
    orum
    -0.14
     REM
    -0.14
     Ñī
    -0.14
     black
    -0.14
     Consortium
    -0.14
    cribe
    -0.13
     twin
    -0.13
     Sylv
    -0.13
    325
    -0.13
    POSITIVE LOGITS
    PILE
    0.16
    ÑĢоÑİ
    0.15
     Careers
    0.15
    ugged
    0.15
    itag
    0.14
    prd
    0.14
    .RightToLeft
    0.14
    IRECTION
    0.14
    ISP
    0.14
    918
    0.14
    Act Density 0.001%

    No Known Activations