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

    Neuronpedia

    INDEX
    Explanations

    references to people and their interactions within a community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugins
    -0.16
    annes
    -0.16
    orgia
    -0.16
     jenter
    -0.15
    habi
    -0.14
    ÑĤин
    -0.14
    飯
    -0.14
    amm
    -0.14
    721
    -0.14
     Extraction
    -0.13
    POSITIVE LOGITS
     visit
    0.42
     visiting
    0.41
     arrive
    0.38
     arrives
    0.36
     visits
    0.36
     arrival
    0.35
     arrived
    0.34
     visita
    0.33
     arriving
    0.33
    visit
    0.33
    Act Density 0.435%

    No Known Activations