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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating hypothetical scenarios or unrealized possibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had" and related past-tense constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.63
    ãģį
    -0.62
     neigh
    -0.62
    CAST
    -0.62
     ru
    -0.62
    女
    -0.61
     scrimmage
    -0.61
    ãĤ¨ãĥ«
    -0.60
    FTWARE
    -0.59
     sacrific
    -0.59
    POSITIVE LOGITS
     they
    0.83
    ering
    0.74
     he
    0.73
     it
    0.72
     there
    0.66
    wolves
    0.66
    cher
    0.65
    ered
    0.65
    soever
    0.64
    itia
    0.63
    Act Density 0.105%

    No Known Activations