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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.17
    pedia
    -0.15
    uf
    -0.14
    ise
    -0.14
     whats
    -0.14
    igraph
    -0.14
    ene
    -0.14
    غ
    -0.14
    ä»Ģä¹Ī
    -0.14
    erson
    -0.14
    POSITIVE LOGITS
    soever
    0.33
     we
    0.21
     they
    0.20
    pring
    0.17
    ÑģÑĮ
    0.17
    oping
    0.17
    upon
    0.16
    plr
    0.15
    SOEVER
    0.15
    antro
    0.15
    Act Density 0.042%

    No Known Activations