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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community engagement, collaboration, and social responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to social relationships and interpersonal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.54
    pload
    -0.52
    uxe
    -0.51
    elected
    -0.49
    aughed
    -0.49
    uable
    -0.49
    addin
    -0.49
    ĵĺ
    -0.48
     Malk
    -0.47
    adra
    -0.47
    POSITIVE LOGITS
     differently
    0.77
     beforehand
    0.64
     patterns
    0.63
    igraph
    0.63
    worthiness
    0.62
     accurately
    0.60
     secrets
    0.59
     correctly
    0.57
     aloud
    0.56
     unfolding
    0.55
    Act Density 1.162%

    No Known Activations