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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs expressing actions or habits

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "used to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bow
    -0.65
    volent
    -0.64
    bitious
    -0.64
    gee
    -0.63
     Hai
    -0.63
     undertaking
    -0.62
    ijing
    -0.61
     defic
    -0.61
     4090
    -0.61
    merce
    -0.60
    POSITIVE LOGITS
     condoms
    0.82
    fully
    0.79
    FUL
    0.74
    fulness
    0.73
     sparing
    0.70
     tires
    0.68
    ãĥ¼ãĥĨãĤ£
    0.66
     extensively
    0.65
     borrowed
    0.62
    nesday
    0.62
    Act Density 0.047%

    No Known Activations