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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "wait" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .»
    -0.73
    ?»
    -0.71
     насељу
    -0.70
    )))),
    -0.69
    )");
    -0.69
    »?
    -0.69
     arcos
    -0.68
    }\}$
    -0.67
     Stephenson
    -0.65
    )»
    -0.65
    POSITIVE LOGITS
     wait
    2.33
     WAIT
    2.09
     waiting
    2.08
    wait
    2.07
     Wait
    2.04
    Wait
    2.00
     waits
    2.00
     waited
    1.93
    WAIT
    1.87
     Waiting
    1.85
    Act Density 0.025%

    No Known Activations