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

    completion of thoughts and statements in written form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.70
    ady
    -0.70
    zel
    -0.68
     disemb
    -0.63
    rue
    -0.62
    awei
    -0.62
     backer
    -0.61
     sleeve
    -0.60
     submerged
    -0.60
     sway
    -0.60
    POSITIVE LOGITS
     âĢ¦"
    1.32
     ..."
    1.24
    }"
    1.21
    .")
    1.18
    )"
    1.08
    )",
    1.08
     Therefore
    1.07
     Especially
    1.06
     Whoever
    1.06
     Hopefully
    1.06
    Act Density 0.252%

    No Known Activations