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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and words related to personal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dma
    -0.16
    mun
    -0.14
    æ´¥
    -0.14
    being
    -0.14
     larg
    -0.13
    418
    -0.13
    hm
    -0.13
    SEM
    -0.13
    imens
    -0.13
    irk
    -0.13
    POSITIVE LOGITS
     alive
    0.17
    ç´Ģ
    0.17
    iola
    0.16
     tabs
    0.15
     hold
    0.15
    _tokenize
    0.15
    enant
    0.15
    èĦ
    0.15
    alive
    0.14
    akes
    0.14
    Act Density 0.032%

    No Known Activations