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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions and transitional phrases that indicate a change in thought or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ameron
    -0.16
    VELO
    -0.14
    afa
    -0.14
    ched
    -0.14
    à¤Ĥध
    -0.14
    izzo
    -0.14
    antiago
    -0.14
     запаÑģ
    -0.14
    anggan
    -0.13
    eparator
    -0.13
    POSITIVE LOGITS
    Ŀ
    0.15
    obbies
    0.15
    eker
    0.15
    urd
    0.14
     Concord
    0.14
    essler
    0.14
     strateg
    0.14
     thought
    0.14
     int
    0.14
     strategy
    0.13
    Act Density 0.089%

    No Known Activations