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

    Neuronpedia

    INDEX
    Explanations

    the word 'which' and similar pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uel
    -0.15
    beck
    -0.13
    cri
    -0.13
    igraph
    -0.13
    uels
    -0.13
     dre
    -0.13
    ysl
    -0.12
    zure
    -0.12
    astic
    -0.12
    Ñģен
    -0.12
    POSITIVE LOGITS
    soever
    0.27
    upon
    0.17
    öh
    0.15
    æķ
    0.15
    weg
    0.14
    ugh
    0.14
    orp
    0.14
    ãĥ¼ãĥ©
    0.14
    peed
    0.14
    plash
    0.13
    Act Density 0.044%

    No Known Activations