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

    Neuronpedia

    INDEX
    Explanations

    dates and locations associated with news events

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to legal and formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pan
    -0.72
    olver
    -0.71
    coat
    -0.67
    Forest
    -0.66
    pled
    -0.66
    entity
    -0.65
    cot
    -0.63
    rats
    -0.63
    assies
    -0.63
    pson
    -0.62
    POSITIVE LOGITS
     jointly
    0.74
     by
    0.72
     BY
    0.67
    lehem
    0.67
    monton
    0.66
     aback
    0.64
     laun
    0.64
     anonymously
    0.64
     aloud
    0.63
     sarcast
    0.62
    Act Density 0.171%

    No Known Activations