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

    Neuronpedia

    INDEX
    Explanations

    specific mathematical symbols and formatting elements used in equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bParam
    -0.67
    Lähde
    -0.63
    ](#
    -0.62
    noinspection
    -0.62
    ❦
    -0.61
     AssemblyCulture
    -0.60
    ilarang
    -0.59
    siąż
    -0.59
    estacks
    -0.59
    bình
    -0.58
    POSITIVE LOGITS
    <eos>
    0.59
    “
    0.55
    )}>
    0.51
    ↵↵↵
    0.50
    ConstraintMaker
    0.50
     <<<<<<<<<<<<<<
    0.49
    ↵
    0.49
    ValueStyle
    0.48
    zap
    0.48
    רושלים
    0.47
    Act Density 1.230%

    No Known Activations