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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by common nouns that represent concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.76
    ))))
    -0.65
    _-
    -0.65
    )))
    -0.64
    then
    -0.62
    netflix
    -0.62
    REDACTED
    -0.62
    ?).
    -0.61
    nesday
    -0.60
    this
    -0.60
    POSITIVE LOGITS
     endeavour
    0.71
     recogn
    0.71
     organis
    0.68
     challenging
    0.66
     endeav
    0.66
     welcoming
    0.65
     adventure
    0.65
     ventures
    0.63
     organisations
    0.63
     ambitious
    0.63
    Act Density 1.622%

    No Known Activations