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

    Neuronpedia

    INDEX
    Explanations

    mentions of enthusiasm or support

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.68
    bal
    -0.64
     Caption
    -0.64
    ridor
    -0.64
     continu
    -0.60
    chie
    -0.59
    DragonMagazine
    -0.58
     earliest
    -0.56
    DK
    -0.56
    IDS
    -0.55
    POSITIVE LOGITS
    ocating
    1.15
    ergic
    1.11
    uring
    1.05
    uding
    1.01
    owed
    0.96
    ocated
    0.96
    ayed
    0.95
     smiles
    0.90
    otted
    0.89
    ying
    0.88
    Act Density 0.042%

    No Known Activations