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

    Neuronpedia

    INDEX
    Explanations

    assertive statements or positions regarding certain topics or situations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to charges and claims in political or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.71
    ETHOD
    -0.63
     sucks
    -0.61
    asus
    -0.61
    orse
    -0.59
    cer
    -0.59
     descriptor
    -0.58
    iversary
    -0.58
     bye
    -0.58
    bilt
    -0.57
    POSITIVE LOGITS
     ranging
    1.05
    ourcing
    0.99
    ynthesis
    0.94
    hops
    0.93
    hooting
    0.90
    cape
    0.89
     pertaining
    0.89
    afety
    0.89
     emanating
    0.85
     abound
    0.85
    Act Density 0.338%

    No Known Activations