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

    Neuronpedia

    INDEX
    Explanations

    words related to legal issues or consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or breaks in the flow of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.65
    abouts
    -0.59
    Availability
    -0.59
    erie
    -0.59
     misunder
    -0.57
     Foundation
    -0.56
    chin
    -0.56
    ãĤ£
    -0.56
    icro
    -0.55
    ophon
    -0.55
    POSITIVE LOGITS
     lest
    1.18
     huh
    1.08
     eh
    1.02
     etc
    1.01
     aka
    0.91
     anyway
    0.88
     thereby
    0.88
     or
    0.87
     preferably
    0.86
     respectively
    0.85
    Act Density 0.509%

    No Known Activations