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

    Neuronpedia

    INDEX
    Explanations

    references to the word "bear" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strar
    -0.18
    yle
    -0.16
    gens
    -0.16
    tz
    -0.16
    yen
    -0.15
    tip
    -0.15
    ching
    -0.15
    BUS
    -0.15
    nid
    -0.15
    ivar
    -0.15
    POSITIVE LOGITS
     witness
    0.35
     Witness
    0.27
    beiten
    0.26
    ance
    0.23
    Witness
    0.22
     bear
    0.21
     Gry
    0.21
     hug
    0.20
    beiter
    0.20
    beit
    0.20
    Act Density 0.020%

    No Known Activations