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

    Neuronpedia

    INDEX
    Explanations

    numerical lists or items marked with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.96
     mosqu
    -0.81
     corrid
    -0.77
     nodd
    -0.74
     predec
    -0.72
     withd
    -0.72
     metic
    -0.70
     proport
    -0.70
     glim
    -0.70
     manif
    -0.69
    POSITIVE LOGITS
     Whether
    0.88
     Besides
    0.87
     However
    0.86
     Specifically
    0.84
     Especially
    0.83
     If
    0.83
     Although
    0.82
     Though
    0.82
     They
    0.82
     Whilst
    0.81
    Act Density 0.765%

    No Known Activations