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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives that characterize individuals positively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzey
    -0.16
     Ñĥдов
    -0.16
    Porno
    -0.14
    rightness
    -0.14
     Happiness
    -0.14
    ukkit
    -0.14
     diligent
    -0.14
    atorium
    -0.13
     Disposable
    -0.13
    ulla
    -0.13
    POSITIVE LOGITS
     outgoing
    0.31
     intro
    0.28
     independent
    0.26
     reserved
    0.25
     caring
    0.25
     strong
    0.24
     extrav
    0.24
     sensitive
    0.23
     independ
    0.21
    intro
    0.21
    Act Density 0.366%

    No Known Activations