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

    Neuronpedia

    INDEX
    Explanations

    technical or academic terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to shifts in perspectives and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.59
    inventoryQuantity
    -0.58
     throats
    -0.57
     cups
    -0.53
     crow
    -0.52
    ãģĹ
    -0.51
     corpses
    -0.50
    volent
    -0.48
    ãģĦ
    -0.47
     Bullets
    -0.47
    POSITIVE LOGITS
     whereby
    0.93
     wherein
    0.80
     regarding
    0.80
     withd
    0.79
    awaru
    0.75
     concerning
    0.71
     relating
    0.69
     insofar
    0.69
    utic
    0.67
     pertaining
    0.67
    Act Density 0.676%

    No Known Activations