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

    Neuronpedia

    INDEX
    Explanations

    references to groups or categories within a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ︎
    -0.86
     McE
    -0.76
    Kön
    -0.76
     Kä
    -0.74
    ://$
    -0.71
     ['./
    -0.71
     interpol
    -0.70
     spalle
    -0.67
    aviar
    -0.66
    обходи
    -0.65
    POSITIVE LOGITS
     group
    1.76
     groups
    1.72
     getGroup
    1.68
     Groups
    1.63
     Group
    1.62
    group
    1.51
    GROUP
    1.51
     GROUP
    1.50
    Group
    1.50
    groups
    1.46
    Act Density 0.086%

    No Known Activations