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

    Neuronpedia

    INDEX
    Explanations

    phrases related to growth or change

    oai_token-act-pair · gpt-3.5-turbo

    significant changes or trends in statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amounted
    -0.45
     transpired
    -0.44
     outwe
    -0.43
     went
    -0.42
     blew
    -0.42
     happened
    -0.41
    OULD
    -0.40
     wraps
    -0.40
     came
    -0.40
    acly
    -0.40
    POSITIVE LOGITS
    "},"
    0.82
    ');
    0.81
    )?
    0.78
    ↵Âł
    0.75
    ¶
    0.75
     Belfast
    0.74
    ↵
    0.73
    )|
    0.72
     (%)
    0.71
    "}
    0.71
    Act Density 0.727%

    No Known Activations