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

    Neuronpedia

    INDEX
    Explanations

    words related to sorting and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fer
    -0.15
     reap
    -0.15
    268
    -0.15
     New
    -0.14
     Stores
    -0.14
    bones
    -0.14
     Tart
    -0.13
    arity
    -0.13
    naments
    -0.13
     and
    -0.13
    POSITIVE LOGITS
    ederland
    0.18
    Configurer
    0.17
    adar
    0.15
    obody
    0.15
    zia
    0.15
    ẫu
    0.14
    grave
    0.14
    /|
    0.14
    opak
    0.14
    ega
    0.14
    Act Density 0.011%

    No Known Activations