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

    Neuronpedia

    INDEX
    Explanations

    references to centers or focal points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omu
    -0.17
    ARGIN
    -0.16
    ÑĮÑİÑĤ
    -0.15
    ument
    -0.14
    mith
    -0.14
    centage
    -0.14
    ائع
    -0.14
     lep
    -0.14
    dar
    -0.14
    lore
    -0.14
    POSITIVE LOGITS
    pieces
    0.24
     hub
    0.22
     nervous
    0.22
    point
    0.21
    fold
    0.21
    hub
    0.20
     focus
    0.20
    focus
    0.20
    most
    0.19
    /core
    0.19
    Act Density 0.047%

    No Known Activations