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

    Neuronpedia

    INDEX
    Explanations

    keywords related to access, such as "Access Hollywood" and "Open Access."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Access" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astically
    -0.69
     sperm
    -0.68
    stal
    -0.66
     Kern
    -0.66
    asm
    -0.65
    annis
    -0.64
     ejac
    -0.63
    GGGG
    -0.61
    pload
    -0.61
    nen
    -0.60
    POSITIVE LOGITS
    ibility
    1.50
    ible
    1.16
    ibly
    1.13
    ibles
    0.99
    ory
    0.98
    IBLE
    0.94
    ibl
    0.93
    ibilities
    0.86
    ion
    0.82
    ured
    0.81
    Act Density 0.029%

    No Known Activations