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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts between different things

    oai_token-act-pair · gpt-3.5-turbo

    connective phrases that introduce comparisons or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.66
    ":[{"
    -0.64
     Pwr
    -0.63
     :=
    -0.62
    ciplinary
    -0.61
    ":-
    -0.61
    iencies
    -0.58
    accompan
    -0.58
    HOU
    -0.56
     ();
    -0.56
    POSITIVE LOGITS
    ?)
    1.42
    !)
    1.37
    !),
    1.33
    ?),
    1.28
    )."
    1.26
    ?).
    1.25
    )
    1.22
    -)
    1.22
    !).
    1.21
    ),"
    1.21
    Act Density 0.181%

    No Known Activations