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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social or communal actions and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostel
    -0.15
    _BATCH
    -0.14
    aine
    -0.14
    UNET
    -0.14
    igne
    -0.14
    PR
    -0.14
    eds
    -0.13
    един
    -0.13
     Destination
    -0.13
     sun
    -0.13
    POSITIVE LOGITS
    ئ
    0.16
    essim
    0.16
    Ñĸно
    0.15
    ummies
    0.15
    _equiv
    0.15
    otte
    0.15
    orden
    0.15
    .ev
    0.14
    erdale
    0.14
    ë
    0.14
    Act Density 0.004%

    No Known Activations