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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.73
     ecosystem
    -0.72
     shadows
    -0.70
    ropy
    -0.67
     critically
    -0.67
     older
    -0.65
     consistency
    -0.65
     fishes
    -0.64
    emic
    -0.64
     eye
    -0.63
    POSITIVE LOGITS
     Later
    0.88
     Afterwards
    0.86
     Again
    0.86
     Presumably
    0.83
     Thankfully
    0.82
     Apparently
    0.81
     Needless
    0.81
     Whilst
    0.81
     Luckily
    0.79
     Seriously
    0.77
    Act Density 1.173%

    No Known Activations