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

    Neuronpedia

    INDEX
    Explanations

    words related to visibility or lack of visibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visibility and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onne
    -0.72
    Union
    -0.69
    itude
    -0.66
    heet
    -0.66
     arr
    -0.65
    nard
    -0.64
    arel
    -0.63
     Wesley
    -0.63
    yre
    -0.62
    inos
    -0.59
    POSITIVE LOGITS
     visibility
    0.92
    ibility
    0.80
    ibly
    0.72
    ilege
    0.71
    ibilities
    0.69
    ileged
    0.67
    DragonMagazine
    0.67
     impaired
    0.67
     goggles
    0.66
    own
    0.65
    Act Density 0.041%

    No Known Activations