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

    Neuronpedia

    INDEX
    Explanations

    references to abstract concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to various "realms" or domains of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.70
    ãģĦ
    -0.67
    TER
    -0.64
    bor
    -0.63
     Clover
    -0.63
    NEY
    -0.61
    HOME
    -0.60
    eph
    -0.59
    PER
    -0.59
    INST
    -0.58
    POSITIVE LOGITS
    naire
    1.00
    osaurs
    0.80
     collide
    0.79
     realms
    0.75
    mares
    0.75
    ality
    0.74
    rums
    0.74
    finder
    0.74
    istry
    0.72
    ationally
    0.72
    Act Density 0.017%

    No Known Activations