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

    Neuronpedia

    INDEX
    Explanations

    words describing characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    nouns and adjectives that create vivid descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Panther
    -0.78
    theless
    -0.66
     PowerPoint
    -0.66
     Accuracy
    -0.64
     Improvement
    -0.63
    Charge
    -0.63
     Wear
    -0.62
     mate
    -0.62
     Origin
    -0.62
    forth
    -0.62
    POSITIVE LOGITS
    itures
    1.13
    acies
    1.12
    icates
    1.05
    ications
    1.02
    ortun
    1.02
    ancies
    1.01
    ials
    1.01
    ues
    0.98
    iae
    0.98
    Ĩ
    0.97
    Act Density 0.121%

    No Known Activations