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

    Neuronpedia

    INDEX
    Explanations

    words related to political or social structures and systems

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns or their derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¾
    -0.73
    erb
    -0.70
    ipeg
    -0.69
    anche
    -0.68
    ods
    -0.68
    ilan
    -0.67
    paren
    -0.65
    enhagen
    -0.64
    iland
    -0.63
    iant
    -0.62
    POSITIVE LOGITS
     thereof
    1.09
     of
    0.90
     wherein
    0.88
     comprising
    0.85
    lain
    0.81
    oft
    0.79
    of
    0.77
     containing
    0.75
    naire
    0.74
     formed
    0.73
    Act Density 0.237%

    No Known Activations