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

    Neuronpedia

    INDEX
    Explanations

    instances of personal introductions and conversational markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç²¾
    -0.16
    .Names
    -0.15
    íģ
    -0.14
    rollo
    -0.14
    _reporting
    -0.14
    baugh
    -0.14
    ervo
    -0.14
    IFY
    -0.14
    оÑĢ
    -0.13
     Confederate
    -0.13
    POSITIVE LOGITS
     jet
    0.15
    ihn
    0.14
    062
    0.14
    astos
    0.14
     me
    0.13
    лÑĥÑĪ
    0.13
     Jet
    0.13
     bro
    0.13
    rire
    0.13
    otype
    0.13
    Act Density 0.001%

    No Known Activations