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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.21
    either
    -0.20
     Either
    -0.20
    Either
    -0.19
     neither
    -0.18
     également
    -0.17
     EITHER
    -0.17
    axon
    -0.16
    ivities
    -0.15
     именно
    -0.15
    POSITIVE LOGITS
     though
    0.30
    -handed
    0.27
    though
    0.26
    Though
    0.24
     worse
    0.23
    ness
    0.22
     Though
    0.22
     sometimes
    0.21
     occasionally
    0.20
    -number
    0.20
    Act Density 0.080%

    No Known Activations