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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that emphasize connections between ideas or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    row
    -0.17
     a
    -0.17
    alla
    -0.15
    {}'.
    -0.14
    resh
    -0.14
    ':['
    -0.14
    ossa
    -0.14
    ashi
    -0.14
    -sector
    -0.13
     svÄĽ
    -0.13
    POSITIVE LOGITS
    ivery
    0.20
     amount
    0.20
     entirety
    0.19
     confines
    0.18
    ìĿ´íĬ¸
    0.17
    orex
    0.15
     multitude
    0.15
     variety
    0.15
    ánchez
    0.15
     ability
    0.14
    Act Density 0.199%

    No Known Activations