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

    Neuronpedia

    INDEX
    Explanations

    references to understanding and interpreting emotions or thoughts of others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vern
    -0.15
    erset
    -0.15
    byt
    -0.14
    bjerg
    -0.14
    punk
    -0.14
    سÙĦ
    -0.14
    apore
    -0.14
     hjem
    -0.13
    .voice
    -0.13
     Arms
    -0.13
    POSITIVE LOGITS
     inner
    0.18
     intros
    0.17
     opaque
    0.17
     Inner
    0.17
     interior
    0.17
     insight
    0.16
    Inner
    0.16
     alien
    0.16
     Hann
    0.16
    inner
    0.16
    Act Density 0.165%

    No Known Activations