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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and variations indicating specific parts or sections of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urovision
    -0.15
    اث
    -0.15
    fid
    -0.14
    ertools
    -0.14
     disproportion
    -0.14
    Ħĸ
    -0.13
     merak
    -0.13
    ffield
    -0.13
    err
    -0.13
    ỡ
    -0.13
    POSITIVE LOGITS
    428
    0.15
     Morrison
    0.13
    {-#
    0.13
    ogr
    0.13
    853
    0.13
    unch
    0.13
    MAND
    0.13
    ĨĴ
    0.13
    789
    0.13
    íĻĺ
    0.13
    Act Density 0.028%

    No Known Activations