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

    Neuronpedia

    INDEX
    Explanations

    explicit references indicating the attribution of statements or opinions to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arest
    -0.71
    cept
    -0.71
    Pont
    -0.68
    aukee
    -0.64
    IELD
    -0.63
    estern
    -0.62
    Tank
    -0.61
    oses
    -0.60
    EMBER
    -0.60
    andem
    -0.59
    POSITIVE LOGITS
     "[
    1.04
     although
    1.03
     '[
    0.83
     whilst
    0.77
     "...
    0.76
    soever
    0.75
     they
    0.74
     "âĢ¦
    0.74
     while
    0.73
     "#
    0.70
    Act Density 0.196%

    No Known Activations