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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating preference or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittest
    -0.18
    flix
    -0.18
    evin
    -0.15
    itm
    -0.15
    duk
    -0.14
    ayne
    -0.14
    rane
    -0.14
    ittle
    -0.14
    ãģĴ
    -0.14
    spÄĽ
    -0.14
    POSITIVE LOGITS
    nt
    0.21
     say
    0.19
     rather
    0.19
     bet
    0.17
     bets
    0.17
     personally
    0.16
    .python
    0.16
     Bet
    0.15
     wager
    0.15
     Rather
    0.15
    Act Density 0.046%

    No Known Activations