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

    Neuronpedia

    INDEX
    Explanations

    explanatory or instructional statements

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing groups or collective states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.74
    é¾įå
    -0.74
    ournal
    -0.71
    swick
    -0.70
    Downloadha
    -0.67
    schild
    -0.66
    Beat
    -0.65
     Whale
    -0.65
    pins
    -0.64
     [/
    -0.62
    POSITIVE LOGITS
    ive
    1.26
    tery
    0.83
    reth
    0.80
    rics
    0.79
    rog
    0.78
    ptic
    0.77
    ives
    0.77
    mble
    0.76
    cery
    0.74
    ãĥ£
    0.74
    Act Density 0.016%

    No Known Activations