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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and related sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilden
    -0.16
     Phong
    -0.15
     spit
    -0.15
    otts
    -0.14
    .vars
    -0.14
    ITHER
    -0.14
    oven
    -0.13
    jez
    -0.13
    educt
    -0.13
    eled
    -0.13
    POSITIVE LOGITS
    amb
    0.20
    endas
    0.16
     Wich
    0.16
    amba
    0.15
    .EventQueue
    0.15
    .ToShort
    0.14
     Bolt
    0.14
     refl
    0.14
    .mongo
    0.14
    άÏĥ
    0.14
    Act Density 0.001%

    No Known Activations