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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different," indicating a focus on contrasts or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.80
     actuels
    -0.72
     Jefus
    -0.70
     BoxFit
    -0.69
    kadang
    -0.67
     különböző
    -0.65
    zeiti
    -0.65
     houſe
    -0.64
     ſmall
    -0.64
     Shakspeare
    -0.64
    POSITIVE LOGITS
    PropertyGroup
    0.58
     EconPapers
    0.51
    相反
    0.50
     unlikely
    0.50
     rewritten
    0.49
     contraire
    0.49
    invoke
    0.49
    Gupta
    0.48
    相比
    0.48
     edit
    0.48
    Act Density 0.238%

    No Known Activations