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

    Neuronpedia

    INDEX
    Explanations

    digits and hexadecimal sequences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     بز
    -0.46
    try
    -0.45
     Al
    -0.43
    localctx
    -0.42
    googleapis
    -0.42
    Al
    -0.42
    kat
    -0.42
    j
    -0.41
    tick
    -0.41
    paper
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.97
     snippetHide
    0.86
    IntoConstraints
    0.83
     سكانية
    0.81
    WriteTagHelper
    0.81
     houſe
    0.79
    FunctionFlags
    0.79
    ViewFeatures
    0.77
    ])))
    0.77
    исленность
    0.76
    Act Density 0.015%

    No Known Activations