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

    Neuronpedia

    INDEX
    Explanations

    mentions of size as a metaphor or literal description

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dwarf" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.83
    anwhile
    -0.79
    inventoryQuantity
    -0.78
    NetMessage
    -0.72
     Wiley
    -0.69
     constitu
    -0.67
    hetti
    -0.66
    endment
    -0.65
     Geo
    -0.64
    ogy
    -0.64
    POSITIVE LOGITS
     dwar
    1.05
     Dwar
    1.01
     dwarves
    0.92
    ven
    0.86
    stein
    0.83
    fs
    0.77
    ptions
    0.76
    fish
    0.75
    pling
    0.73
     dwarf
    0.72
    Act Density 0.005%

    No Known Activations