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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gaining entry or obtaining permission to something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     almond
    -0.65
     scra
    -0.65
     Kern
    -0.62
     sperm
    -0.59
    annis
    -0.59
     flower
    -0.59
     Gael
    -0.59
    birds
    -0.58
     ejac
    -0.58
     condol
    -0.57
    POSITIVE LOGITS
    ibility
    1.36
    ibly
    1.19
    ible
    1.07
    ibilities
    0.91
    ibl
    0.90
    ibles
    0.89
    ion
    0.88
    ioned
    0.87
     privileges
    0.86
    ory
    0.86
    Act Density 0.021%

    No Known Activations