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

    Neuronpedia

    INDEX
    Explanations

    instances of being informed or directed by others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dre
    -0.18
    mdi
    -0.15
     itself
    -0.15
    зÑĭ
    -0.15
    vailability
    -0.15
     themselves
    -0.14
    emek
    -0.14
    Acknowled
    -0.14
     çek
    -0.14
    YLON
    -0.14
    POSITIVE LOGITS
    stery
    0.15
    ayo
    0.15
     Situation
    0.14
    edi
    0.14
    enberg
    0.14
    semb
    0.14
     simultaneously
    0.14
    åĻ
    0.14
     Princip
    0.14
     Yok
    0.14
    Act Density 0.043%

    No Known Activations