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

    Neuronpedia

    INDEX
    Explanations

    references to Charles Darwin and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     armed
    -0.16
    erties
    -0.15
    gers
    -0.15
    tte
    -0.15
    ihan
    -0.15
    ihat
    -0.15
    ited
    -0.14
    dde
    -0.14
     hy
    -0.14
    Titles
    -0.14
    POSITIVE LOGITS
    lington
    0.26
    kest
    0.26
    win
    0.26
    lene
    0.26
    fur
    0.25
    rell
    0.25
    wins
    0.24
    lings
    0.23
    rien
    0.23
    ÃŃo
    0.22
    Act Density 0.010%

    No Known Activations