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

    Neuronpedia

    INDEX
    Explanations

    sentences describing personal experiences or activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and commas indicating the end of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ue
    -0.73
     unequ
    -0.72
     criminal
    -0.71
     submerged
    -0.69
    uers
    -0.69
     opposing
    -0.69
    ibur
    -0.69
    imb
    -0.67
    ues
    -0.67
     bonded
    -0.66
    POSITIVE LOGITS
     Thankfully
    1.21
     Luckily
    1.18
     My
    1.14
     Fortunately
    1.14
     Unfortunately
    1.13
     Hopefully
    1.12
     However
    1.06
     Sadly
    1.06
     Honestly
    1.06
     Personally
    1.05
    Act Density 0.649%

    No Known Activations