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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods indicating sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trickle
    -0.78
     grip
    -0.76
     quir
    -0.76
     strangers
    -0.74
     shy
    -0.72
     hug
    -0.72
     everywhere
    -0.71
     etiquette
    -0.70
     poke
    -0.70
     fancy
    -0.70
    POSITIVE LOGITS
     Additionally
    1.47
     Furthermore
    1.23
     Specifically
    1.15
    Downloadha
    1.13
     However
    1.13
     Previously
    1.12
    Additionally
    1.11
     Therefore
    1.08
     Also
    1.07
     Consequently
    1.07
    Act Density 0.521%

    No Known Activations