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

    Neuronpedia

    INDEX
    Explanations

    mathematical equalities and operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    weck
    -0.54
    protoc
    -0.52
    ấc
    -0.49
    HasKey
    -0.48
     архивлан
    -0.48
     bParam
    -0.48
     Bax
    -0.47
    )"),
    -0.47
    werve
    -0.46
    胆
    -0.46
    POSITIVE LOGITS
    ArrowToggle
    0.62
    ensement
    0.58
    getMenuInflater
    0.55
     aérea
    0.55
     possesso
    0.54
    tonsoft
    0.53
    üttel
    0.53
     geçti
    0.52
    :][
    0.51
    ">—
    0.51
    Act Density 0.014%

    No Known Activations