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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "share" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ape
    -0.18
    ritz
    -0.18
    ago
    -0.16
    erness
    -0.15
     ÑģобÑĸ
    -0.14
    ockets
    -0.14
    go
    -0.14
    orphic
    -0.14
    amientos
    -0.13
    _GU
    -0.13
    POSITIVE LOGITS
     stories
    0.20
     secrets
    0.20
     experiences
    0.19
     knowledge
    0.19
     with
    0.17
    knowledge
    0.17
     thoughts
    0.16
     information
    0.16
     story
    0.16
     μαζί
    0.16
    Act Density 0.030%

    No Known Activations