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

    Neuronpedia

    INDEX
    Explanations

    references to groups or collections of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _group
    -0.19
    éĽĨåĽ¢
    -0.19
     grouped
    -0.18
    ry
    -0.18
    _groups
    -0.17
    eri
    -0.17
    Group
    -0.17
    Groups
    -0.16
    _GROUPS
    -0.16
    hone
    -0.16
    POSITIVE LOGITS
    ings
    0.44
    think
    0.28
    INGS
    0.27
    usc
    0.25
    sWith
    0.22
    aroo
    0.20
    ware
    0.19
     hug
    0.19
    ement
    0.19
    mates
    0.19
    Act Density 0.064%

    No Known Activations