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

    Neuronpedia

    INDEX
    Explanations

    references to notable literary works and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶Į
    -0.17
    nex
    -0.15
    scoped
    -0.15
    åĥ
    -0.15
    .cy
    -0.14
    ounge
    -0.14
    iece
    -0.14
    æĻ´
    -0.14
    .ak
    -0.14
    ainting
    -0.14
    POSITIVE LOGITS
     fair
    0.36
     fairy
    0.28
     Fairy
    0.27
     Fair
    0.26
    fair
    0.26
    Fair
    0.23
     Peter
    0.23
     Alice
    0.22
     fa
    0.21
     faire
    0.21
    Act Density 0.062%

    No Known Activations