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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting specific to equations and formal proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reese
    -0.41
     Reich
    -0.39
     Ré
    -0.38
    Reich
    -0.36
     Reim
    -0.35
    Ré
    -0.35
     Rech
    -0.34
    Reese
    -0.34
    red
    -0.34
    ré
    -0.34
    POSITIVE LOGITS
     ro
    2.31
     Ro
    2.09
    Ro
    1.99
     RO
    1.85
    RO
    1.81
     Ро
    1.78
    ro
    1.76
     ро
    1.63
     rosette
    1.60
    Ро
    1.58
    Act Density 1.410%

    No Known Activations