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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate choice or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Either
    -0.21
    Either
    -0.19
     either
    -0.19
     både
    -0.18
    either
    -0.17
    enheim
    -0.17
     nejen
    -0.16
    aday
    -0.15
    anca
    -0.15
     nawet
    -0.15
    POSITIVE LOGITS
     way
    0.31
    /or
    0.30
    -way
    0.28
     side
    0.28
    way
    0.26
    /all
    0.23
    -than
    0.23
     party
    0.23
    -or
    0.23
     directly
    0.22
    Act Density 0.025%

    No Known Activations