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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.17
    igraph
    -0.16
    ald
    -0.15
    ouv
    -0.14
    غ
    -0.14
    wor
    -0.14
    ære
    -0.14
     what
    -0.14
    erson
    -0.14
    adil
    -0.14
    POSITIVE LOGITS
    soever
    0.32
     we
    0.18
    andler
    0.17
    pring
    0.16
    oping
    0.16
    ÑģÑĮ
    0.16
    oot
    0.15
     they
    0.15
    imler
    0.15
    SOEVER
    0.15
    Act Density 0.038%

    No Known Activations