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

    Neuronpedia

    INDEX
    Explanations

    the presence of relationships that involve dependency or support

    oai_token-act-pair · gpt-3.5-turbo

    references to the presence or need for individuals in various roles within social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wast
    -0.72
    ovember
    -0.66
    ãĥ¼ãĤ¯
    -0.66
    utenberg
    -0.61
     Maze
    -0.59
    æĸ
    -0.57
     Manufact
    -0.57
     incorrectly
    -0.57
     culmin
    -0.56
     Decay
    -0.55
    POSITIVE LOGITS
     willing
    1.25
     nearby
    1.01
    hip
    0.98
     guiding
    0.96
     whom
    0.96
     capable
    0.93
     overseeing
    0.93
     trustworthy
    0.91
     who
    0.88
     handy
    0.88
    Act Density 0.421%

    No Known Activations