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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orum
    -0.17
    ajs
    -0.17
    anh
    -0.16
    VERR
    -0.16
    à¹ģรà¸ĩ
    -0.15
    itele
    -0.15
    antis
    -0.15
    ottage
    -0.14
    orre
    -0.14
     pov
    -0.14
    POSITIVE LOGITS
     leads
    0.14
     Wich
    0.14
    .misc
    0.14
    ÙģÙĤ
    0.14
     naturally
    0.14
    oten
    0.14
     Maxwell
    0.13
    endon
    0.13
    emi
    0.13
     means
    0.13
    Act Density 0.078%

    No Known Activations