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

    Neuronpedia

    INDEX
    Explanations

    references to snakes or snake-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otron
    -0.16
    isay
    -0.16
    inger
    -0.15
     Umb
    -0.15
    aise
    -0.15
    534
    -0.15
    ume
    -0.15
    undry
    -0.14
    portun
    -0.14
    ounding
    -0.14
    POSITIVE LOGITS
     sn
    0.40
     Sn
    0.32
    sn
    0.32
    /sn
    0.31
    (sn
    0.30
    .Sn
    0.29
    -sn
    0.28
    Sn
    0.27
    .sn
    0.27
     SN
    0.27
    Act Density 0.016%

    No Known Activations