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

    Neuronpedia

    INDEX
    Explanations

    references to transformative events or changes in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.60
     })
    -0.55
     estekak
    -0.55
    setDo
    -0.54
     geslacht
    -0.53
    ScopeManager
    -0.52
     Aurang
    -0.51
     DialogInterface
    -0.50
    emploi
    -0.49
     Bilingual
    -0.49
    POSITIVE LOGITS
     fictional
    0.67
    humans
    0.58
     đảo
    0.56
    populated
    0.54
    modern
    0.52
     town
    0.52
     humains
    0.52
    isolated
    0.52
     populated
    0.51
    Sector
    0.51
    Act Density 0.277%

    No Known Activations