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

    Neuronpedia

    INDEX
    Explanations

    characteristics related to personality traits and moral values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gezocht
    -0.14
    ush
    -0.14
    uzzi
    -0.14
    own
    -0.14
    ince
    -0.13
    iska
    -0.13
    elles
    -0.13
    omat
    -0.13
    bo
    -0.13
    },{↵
    -0.13
    POSITIVE LOGITS
     entity
    0.26
     affair
    0.20
     creatures
    0.20
     creature
    0.19
     enough
    0.18
     Entity
    0.18
     entities
    0.18
     ENTITY
    0.18
    entity
    0.17
     institution
    0.17
    Act Density 0.190%

    No Known Activations