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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.80
     mosqu
    -0.74
     manif
    -0.72
     amph
    -0.71
     nuts
    -0.71
     charact
    -0.70
     diseng
    -0.68
     ogre
    -0.67
     defe
    -0.67
     fermented
    -0.65
    POSITIVE LOGITS
     Specifically
    1.00
     Its
    0.97
     Though
    0.96
     Whether
    0.94
     Previously
    0.94
     While
    0.93
     However
    0.93
     Although
    0.93
     They
    0.91
     Their
    0.89
    Act Density 0.786%

    No Known Activations