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

    Neuronpedia

    INDEX
    Explanations

    references to gaining the ability to reach or use something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "access" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbollah
    -0.68
    deal
    -0.65
    achy
    -0.63
    fare
    -0.63
    poly
    -0.62
    price
    -0.61
    break
    -0.61
     quart
    -0.59
    friend
    -0.59
    inning
    -0.58
    POSITIVE LOGITS
    ibly
    0.97
    ibility
    0.92
     Wikipedia
    0.74
    ible
    0.73
    folios
    0.72
    ioned
    0.72
    ories
    0.71
    ADRA
    0.70
    İĭ
    0.69
    IBLE
    0.69
    Act Density 0.078%

    No Known Activations