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

    Neuronpedia

    INDEX
    Explanations

    the word "at" in various contexts and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erator
    -0.17
    iston
    -0.17
    hard
    -0.16
    à¥įण
    -0.16
    erer
    -0.15
    ering
    -0.15
    ermann
    -0.15
    eration
    -0.15
    halt
    -0.14
    ões
    -0.14
    POSITIVE LOGITS
    tempts
    0.19
    roc
    0.17
    rop
    0.17
    temp
    0.17
     least
    0.17
    rophy
    0.17
    lassian
    0.17
    -home
    0.17
    kinson
    0.17
    elier
    0.16
    Act Density 0.335%

    No Known Activations