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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to social structures and cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okud
    -0.14
    ÅĻ
    -0.14
    .uml
    -0.13
     Gilles
    -0.13
    aky
    -0.13
    rove
    -0.12
    upy
    -0.12
     Spray
    -0.12
    باش
    -0.12
     unary
    -0.12
    POSITIVE LOGITS
     alike
    0.26
    ortal
    0.15
    åľĪ
    0.14
    ationToken
    0.14
     etc
    0.14
    essen
    0.14
    /../
    0.14
     serta
    0.14
    ãĥīãĥ«
    0.14
     apprec
    0.13
    Act Density 1.190%

    No Known Activations