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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outcomes and results

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating results or outcomes of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.76
    yi
    -0.74
    terday
    -0.73
    igraph
    -0.72
    addons
    -0.71
     aloud
    -0.67
    stan
    -0.67
    udi
    -0.63
    Enlarge
    -0.63
     mant
    -0.62
    POSITIVE LOGITS
     predictable
    0.98
     unequal
    0.81
     unpredictable
    0.77
    ãĥĩãĤ£
    0.76
     predictably
    0.74
     unsur
    0.73
    ãĥķãĤ©
    0.73
     disappointing
    0.73
     unsatisf
    0.71
     remarkable
    0.70
    Act Density 0.138%

    No Known Activations