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

    Neuronpedia

    INDEX
    Explanations

    the verb form "s" indicating possession or personalization

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.59
     Observ
    -0.58
     Continental
    -0.57
     Rounds
    -0.57
    roit
    -0.55
     Britons
    -0.54
     Refer
    -0.52
     Industries
    -0.52
     Rebell
    -0.52
     WARN
    -0.52
    POSITIVE LOGITS
     plenty
    1.09
    omething
    1.04
     nothing
    0.97
    been
    0.92
     been
    0.91
    nothing
    0.88
    little
    0.88
     gotta
    0.86
     alot
    0.86
     gonna
    0.86
    Act Density 0.036%

    No Known Activations