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

    Neuronpedia

    INDEX
    Explanations

    the concept of "work" and various forms of its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alsy
    -0.17
    cki
    -0.16
    æĺŃ
    -0.15
    oria
    -0.14
    èĢĥ
    -0.14
    apl
    -0.14
    ELLOW
    -0.14
    ateria
    -0.14
    ORIA
    -0.14
    indent
    -0.14
    POSITIVE LOGITS
     backward
    0.21
     out
    0.21
     toward
    0.20
     towards
    0.20
     harder
    0.19
     backwards
    0.19
     magic
    0.17
    shopping
    0.17
    ozem
    0.16
     through
    0.16
    Act Density 0.042%

    No Known Activations