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

    Neuronpedia

    INDEX
    Explanations

    terms related to political discussions and nominations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.75
    ArrowToggle
    -0.64
    Geplaatst
    -0.63
    AnchorStyles
    -0.59
    bitField
    -0.59
    AttributeSet
    -0.57
     ModelExpression
    -0.56
    CodeAttribute
    -0.56
     insuffisamment
    -0.56
    EndContext
    -0.54
    POSITIVE LOGITS
     magically
    0.56
    ouser
    0.47
      (
    0.46
    feldt
    0.46
    ूट
    0.46
     magic
    0.45
    instead
    0.45
    Magic
    0.44
    }))
    0.44
    magic
    0.44
    Act Density 0.224%

    No Known Activations