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

    Neuronpedia

    INDEX
    Explanations

    references to the word "vis" which could be associated with visits, visions, visualization, or names containing "vis" like Travis or invisible

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vis" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.71
    ¶ħ
    -0.69
     fractions
    -0.65
     towed
    -0.62
     separating
    -0.62
     tender
    -0.61
     piling
    -0.61
     doomed
    -0.61
     Carnegie
    -0.60
    ascal
    -0.60
    POSITIVE LOGITS
    ibility
    1.41
    vis
    1.18
    itors
    1.17
    ibly
    1.11
    itor
    1.08
    ascus
    0.98
    ited
    0.95
    ible
    0.95
    ibl
    0.94
    ision
    0.93
    Act Density 0.004%

    No Known Activations