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

    Neuronpedia

    INDEX
    Explanations

    usage of transitional phrases that indicate contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeÅĦ
    -0.16
     Halk
    -0.14
    .hw
    -0.14
    isay
    -0.14
    istrovstvÃŃ
    -0.13
    mî
    -0.13
    ocre
    -0.13
    ilha
    -0.13
    ouce
    -0.13
    uces
    -0.13
    POSITIVE LOGITS
    /or
    0.16
    lem
    0.14
    âĤ¬“
    0.14
    .infinity
    0.14
    atr
    0.13
    езда
    0.13
     bordel
    0.13
    verts
    0.13
    ÅĽ
    0.12
    umi
    0.12
    Act Density 0.177%

    No Known Activations