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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sher
    -0.16
    inflate
    -0.15
    itet
    -0.15
    rp
    -0.15
    è±
    -0.14
     Ãĸn
    -0.14
    輪
    -0.14
     teb
    -0.14
    licht
    -0.14
    .inst
    -0.14
    POSITIVE LOGITS
    oyal
    0.18
    airs
    0.16
    free
    0.15
    eten
    0.14
     Holiday
    0.14
    etti
    0.14
    ilk
    0.14
    icas
    0.14
    -about
    0.14
    ">//
    0.14
    Act Density 0.026%

    No Known Activations