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

    Neuronpedia

    INDEX
    Explanations

    instances of social interactions and encounters, especially involving strangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beef
    -0.16
    uche
    -0.15
    425
    -0.15
    ocha
    -0.15
    agn
    -0.14
    itzer
    -0.14
     Beef
    -0.14
    ocr
    -0.14
    ÃŃt
    -0.13
    .sorted
    -0.13
    POSITIVE LOGITS
    amar
    0.17
    vi
    0.16
    fsp
    0.15
     stranger
    0.15
    ró
    0.14
    vie
    0.14
    owan
    0.14
    undles
    0.14
    lop
    0.13
    antom
    0.13
    Act Density 0.006%

    No Known Activations