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

    Neuronpedia

    INDEX
    Explanations

    instances of 'or' and other alternatives in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.21
    swer
    -0.19
    нÑİ
    -0.18
    empo
    -0.18
    venir
    -0.17
    ì¹
    -0.16
    emas
    -0.15
    seys
    -0.15
    -0.15
    /OR
    -0.15
    POSITIVE LOGITS
    ignal
    0.28
     Bust
    0.27
    ourke
    0.26
     bust
    0.24
    anged
    0.24
    anging
    0.24
    phans
    0.23
    acles
    0.23
    ator
    0.22
    angen
    0.21
    Act Density 0.143%

    No Known Activations