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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "so" used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Everybody
    -0.89
     Everybody
    -0.86
     everybody
    -0.81
     guys
    -0.76
    everybody
    -0.75
     scared
    -0.72
     stupid
    -0.71
     people
    -0.67
    Nobody
    -0.67
    tabular
    -0.65
    POSITIVE LOGITS
     thereof
    0.80
    الدراسه
    0.80
     tevens
    0.76
     therein
    0.76
     TestBed
    0.74
    ՝
    0.74
    Datuak
    0.72
     springfox
    0.72
    Архівовано
    0.72
    ArrowToggle
    0.71
    Act Density 0.411%

    No Known Activations