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

    Neuronpedia

    INDEX
    Explanations

    terms related to isolation and personal struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    777
    -0.15
     Gran
    -0.15
    ppo
    -0.15
    ÑĢива
    -0.15
     gran
    -0.14
     aç
    -0.14
    loh
    -0.14
     wind
    -0.14
    lys
    -0.14
    Gran
    -0.14
    POSITIVE LOGITS
     Alien
    0.40
     Ali
    0.33
    Ali
    0.33
     Rip
    0.32
     alien
    0.29
     Ridley
    0.28
     Xen
    0.28
    ALI
    0.27
    alien
    0.27
     xen
    0.26
    Act Density 0.008%

    No Known Activations