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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "revision" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gamba
    -0.56
    IGraphics
    -0.55
     Battista
    -0.54
     Portuguesa
    -0.53
    ObjectMeta
    -0.52
    jeno
    -0.51
     compagni
    -0.51
     fekete
    -0.51
    سكرية
    -0.50
     mecán
    -0.50
    POSITIVE LOGITS
     residual
    1.23
     residue
    1.12
     residues
    1.07
    residual
    1.02
    resid
    1.00
     Residual
    1.00
     revision
    0.98
    residue
    0.96
    Residue
    0.94
     residuals
    0.93
    Act Density 0.085%

    No Known Activations