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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uction
    -0.18
    laus
    -0.17
    ignKey
    -0.16
    oucher
    -0.15
    antine
    -0.15
    oti
    -0.15
     none
    -0.15
    eç
    -0.15
    hra
    -0.15
    -op
    -0.15
    POSITIVE LOGITS
     ally
    0.23
     tall
    0.23
    ally
    0.20
     Tall
    0.20
     alle
    0.20
    al
    0.18
     ll
    0.18
     altogether
    0.17
     al
    0.16
     ail
    0.16
    Act Density 0.011%

    No Known Activations