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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or kernels within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.84
    Tikang
    -0.74
     MenuView
    -0.73
    esez
    -0.70
    StructEnd
    -0.67
    antaranya
    -0.66
    setVerticalGroup
    -0.65
     Efq
    -0.65
     Theſe
    -0.65
    LEncoder
    -0.65
    POSITIVE LOGITS
    spin
    0.47
    rawDesc
    0.47
    num
    0.46
    bran
    0.46
     spin
    0.46
    moor
    0.45
     setOpen
    0.45
     Cas
    0.44
     num
    0.44
     resourceCulture
    0.44
    Act Density 0.001%

    No Known Activations