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

    Neuronpedia

    INDEX
    Explanations

    mentions of inclusion or belonging in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "among" indicating groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prol
    -0.73
    di
    -0.72
    oulos
    -0.69
    Clar
    -0.68
    emb
    -0.66
    nas
    -0.65
    abb
    -0.65
    iris
    -0.64
    oldemort
    -0.62
    ricanes
    -0.62
    POSITIVE LOGITS
    Īè
    0.84
     whom
    0.79
    among
    0.78
     among
    0.75
     amongst
    0.72
    wart
    0.71
    IJ
    0.71
    warts
    0.71
     peers
    0.71
    ĨĴ
    0.70
    Act Density 0.025%

    No Known Activations