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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of "being" or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ckt
    -0.18
    /remove
    -0.18
    ulumi
    -0.14
    urray
    -0.14
    ocator
    -0.14
    mlin
    -0.14
     çĿ
    -0.14
    erset
    -0.14
    μβ
    -0.14
    anvas
    -0.14
    POSITIVE LOGITS
    ness
    0.35
     able
    0.26
     unable
    0.23
     apart
    0.18
     told
    0.18
     part
    0.18
    NESS
    0.18
     Able
    0.17
     asked
    0.17
    ly
    0.16
    Act Density 0.056%

    No Known Activations