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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of inevitability or universality in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kop
    -0.17
     suspense
    -0.15
    ssi
    -0.14
    egers
    -0.14
    jin
    -0.14
    oter
    -0.14
    jerne
    -0.14
    uhn
    -0.14
    stasy
    -0.14
    .readString
    -0.14
    POSITIVE LOGITS
     how
    0.19
     whether
    0.18
    whether
    0.17
    how
    0.17
    å¤ļå°ij
    0.17
    865
    0.15
    fully
    0.15
    obo
    0.15
    /how
    0.15
     Äijâu
    0.14
    Act Density 0.011%

    No Known Activations