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

    Neuronpedia

    INDEX
    Explanations

    conjunctive and transitional phrases that indicate logical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daf
    -0.60
     Plin
    -0.57
     Efq
    -0.57
     SRS
    -0.56
     Cyl
    -0.56
     seashore
    -0.56
     cylinders
    -0.56
     fowls
    -0.55
     fools
    -0.55
     certiorari
    -0.55
    POSITIVE LOGITS
    invokeLater
    0.79
    EndContext
    0.74
    IndentedString
    0.71
    ChildScrollView
    0.71
    setVerticalGroup
    0.70
     Thus
    0.68
    دانشنامهٔ
    0.68
     ProtoMessage
    0.67
     通販
    0.66
     OMITBAD
    0.65
    Act Density 0.592%

    No Known Activations