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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ir" with different combinations of letters before and after it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quir" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļé
    -0.66
     Takeru
    -0.60
     Tenn
    -0.59
    raised
    -0.59
    alter
    -0.58
     Xuan
    -0.58
     Vinyl
    -0.58
     untreated
    -0.57
    erker
    -0.56
     Dragonbound
    -0.56
    POSITIVE LOGITS
    vana
    1.23
    rha
    1.08
    ROR
    1.07
    andom
    1.02
    ror
    0.94
    mingham
    0.94
    cles
    0.93
    idium
    0.90
    oux
    0.87
    bid
    0.87
    Act Density 0.037%

    No Known Activations