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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "similar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometr
    -0.15
    urum
    -0.14
    ë©ĺ
    -0.14
    è¬
    -0.14
     particular
    -0.14
    efeller
    -0.14
    ezi
    -0.13
    .simps
    -0.13
    gota
    -0.13
    ember
    -0.13
    POSITIVE LOGITS
    ily
    0.46
    ities
    0.28
     vein
    0.27
    -looking
    0.26
    -sized
    0.26
     sized
    0.26
     sounding
    0.24
     enough
    0.24
    ity
    0.24
     minded
    0.24
    Act Density 0.056%

    No Known Activations