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

    Neuronpedia

    INDEX
    Explanations

    keywords related to sharing information or experiences with others

    oai_token-act-pair · gpt-3.5-turbo

    references to sharing and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.74
     submar
    -0.61
    ij
    -0.60
    lesi
    -0.58
     hurd
    -0.58
     Secondly
    -0.57
    tarians
    -0.57
    IOR
    -0.57
    ¯
    -0.57
    ª
    -0.56
    POSITIVE LOGITS
     secrets
    0.92
     with
    0.90
     peacefully
    0.80
    ware
    0.74
     burden
    0.74
    Tweet
    0.73
     knowledge
    0.73
     workspace
    0.73
     With
    0.72
     burdens
    0.72
    Act Density 0.124%

    No Known Activations