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

    Neuronpedia

    INDEX
    Explanations

    references to dolls and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Helm
    -0.15
     Ridley
    -0.14
    ocator
    -0.14
     Rao
    -0.14
    ezi
    -0.14
    ragon
    -0.14
    estone
    -0.14
    oku
    -0.14
    ectar
    -0.13
    _CLIENT
    -0.13
    POSITIVE LOGITS
     dolls
    0.33
     doll
    0.32
     figures
    0.26
     Doll
    0.25
    doll
    0.24
     toys
    0.23
    figures
    0.22
     figure
    0.22
     Figures
    0.21
     toy
    0.20
    Act Density 0.097%

    No Known Activations