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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs, specifically focusing on actions that happened at a certain age of a person

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "was" in various contexts, indicating a focus on past experiences or memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WER
    -0.74
    atories
    -0.67
    sonian
    -0.67
    oids
    -0.67
    ologies
    -0.64
    ological
    -0.63
    lly
    -0.62
    do
    -0.60
    metry
    -0.60
    Comments
    -0.58
    POSITIVE LOGITS
     seated
    0.80
     touring
    0.79
     confronted
    0.78
     gearing
    0.77
     introduced
    0.77
     reunited
    0.77
     able
    0.76
     tasked
    0.75
     briefed
    0.75
     supposed
    0.74
    Act Density 0.161%

    No Known Activations