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

    Neuronpedia

    INDEX
    Explanations

    references to different groups or categories within data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ︎
    -0.79
     McE
    -0.78
    Kön
    -0.75
     ['./
    -0.75
     Kä
    -0.70
     interpol
    -0.69
    ://$
    -0.66
     étoile
    -0.66
     spalle
    -0.64
    뮬
    -0.63
    POSITIVE LOGITS
     group
    2.13
     groups
    2.05
     Group
    1.96
     Groups
    1.94
     getGroup
    1.92
    group
    1.87
    Group
    1.86
     GROUP
    1.82
    GROUP
    1.79
    groups
    1.75
    Act Density 0.098%

    No Known Activations