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

    Neuronpedia

    INDEX
    Explanations

    phrases or references to specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -1.02
    WriteBarrier
    -0.85
    EndContext
    -0.84
    fjspx
    -0.82
    rungsseite
    -0.81
    StructEnd
    -0.76
    __*/
    -0.75
    )");
    -0.75
    adaptiveStyles
    -0.74
    EndGlobalSection
    -0.71
    POSITIVE LOGITS
     prior
    0.58
     initially
    0.53
    Originally
    0.52
     initial
    0.52
     originally
    0.49
     Initially
    0.48
    orig
    0.46
     original
    0.46
     before
    0.46
    ณ
    0.45
    Act Density 0.406%

    No Known Activations