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

    Neuronpedia

    INDEX
    Explanations

    titles and notable figures in literature and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchos
    -0.18
    iece
    -0.15
    ¶Į
    -0.15
    CACHE
    -0.15
    åĥ
    -0.15
    agma
    -0.15
    Forge
    -0.14
    .ak
    -0.14
    ounge
    -0.14
     Eisenhower
    -0.14
    POSITIVE LOGITS
     fair
    0.36
     fairy
    0.32
     Fairy
    0.30
    fair
    0.26
     Fair
    0.26
     Ñģказ
    0.26
     Alice
    0.24
    Fair
    0.23
     Grimm
    0.23
     fa
    0.20
    Act Density 0.149%

    No Known Activations