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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or official actions, such as "ticketed", "commissioned", and "summons"

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.77
     Leilan
    -0.74
    å£
    -0.70
    FTWARE
    -0.66
    åħī
    -0.66
    ORY
    -0.64
    ãĥ¯ãĥ³
    -0.62
    orest
    -0.62
    irlf
    -0.59
    ufact
    -0.59
    POSITIVE LOGITS
    nesday
    0.98
    uled
    0.92
    ict
    0.85
    uct
    0.82
    dit
    0.82
    own
    0.81
    ging
    0.78
     aback
    0.77
    ouble
    0.77
    icated
    0.74
    Act Density 0.062%

    No Known Activations