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

    Neuronpedia

    INDEX
    Explanations

    phrases used for presenting lists or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.67
    XmlAccessorType
    -0.66
     himſelf
    -0.66
     myſelf
    -0.63
     Suez
    -0.62
     pinulongan
    -0.61
     Jefus
    -0.61
    esgue
    -0.60
     reafon
    -0.60
     caufe
    -0.59
    POSITIVE LOGITS
    Firstly
    1.15
     Firstly
    1.10
    まず
    1.05
    首先
    1.04
     firstly
    1.00
     First
    0.96
    First
    0.95
    первых
    0.92
    Primero
    0.88
    abord
    0.86
    Act Density 0.396%

    No Known Activations