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

    Neuronpedia

    INDEX
    Explanations

    terms related to necessity and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.15
    afil
    -0.15
    umat
    -0.15
     imp
    -0.14
    pering
    -0.14
     modern
    -0.14
     cmdline
    -0.14
    adi
    -0.14
    324
    -0.14
     Works
    -0.13
    POSITIVE LOGITS
    thur
    0.16
    Interop
    0.16
    udder
    0.15
    æ´
    0.15
    ativa
    0.15
     Ness
    0.14
    çļ
    0.14
    çıį
    0.14
    VERTISE
    0.14
    Heap
    0.14
    Act Density 0.065%

    No Known Activations