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

    Neuronpedia

    INDEX
    Explanations

    phrases related to in-house development and capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzey
    -0.18
    rak
    -0.15
    aida
    -0.15
     Unblock
    -0.15
    paque
    -0.14
    ADR
    -0.14
    -chevron
    -0.14
    annah
    -0.14
    óa
    -0.14
    uur
    -0.14
    POSITIVE LOGITS
     own
    0.42
     Own
    0.36
    own
    0.34
    Own
    0.33
     OWN
    0.29
    _own
    0.29
    èĩªå·±çļĦ
    0.29
     directly
    0.28
     próp
    0.27
     direct
    0.27
    Act Density 0.166%

    No Known Activations