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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyse
    -0.16
    -await
    -0.16
    Ø·ÙĨ
    -0.15
    znik
    -0.15
    ashtra
    -0.15
    IJľ
    -0.14
    querque
    -0.14
     yoksa
    -0.14
    ãĥĨãĥ«
    -0.14
    ippi
    -0.14
    POSITIVE LOGITS
     reality
    0.20
    nable
    0.17
    129
    0.16
     realities
    0.16
    nes
    0.16
     Reality
    0.16
    alone
    0.15
    ör
    0.15
     flip
    0.15
     direction
    0.15
    Act Density 0.028%

    No Known Activations