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

    Neuronpedia

    INDEX
    Explanations

    the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usz
    -0.16
    rai
    -0.16
    anche
    -0.15
    Ptr
    -0.15
    887
    -0.13
    137
    -0.13
    atures
    -0.13
    876
    -0.13
     Anc
    -0.13
    zelf
    -0.13
    POSITIVE LOGITS
     sino
    0.17
    inson
    0.16
    ebek
    0.15
    úsqueda
    0.15
     th
    0.14
    ãĥ©ãĥ³ãĥī
    0.14
    Äħd
    0.14
    ÅĽcie
    0.14
    cth
    0.14
    áj
    0.14
    Act Density 0.014%

    No Known Activations