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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOY
    -0.14
    .quest
    -0.14
     Muk
    -0.14
    zas
    -0.14
    burgh
    -0.13
    utex
    -0.13
    ddb
    -0.13
    iminal
    -0.13
    ritz
    -0.13
     Cosmos
    -0.13
    POSITIVE LOGITS
     sir
    0.64
     Sir
    0.52
    Sir
    0.50
    åħĪçĶŁ
    0.35
     Mr
    0.34
    Mr
    0.31
     boss
    0.27
     Boss
    0.24
    Boss
    0.23
     Professor
    0.21
    Act Density 0.572%

    No Known Activations