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

    Neuronpedia

    INDEX
    Explanations

    occurrences of verbs related to achieving or meeting criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Named
    -0.23
    Designed
    -0.22
    _named
    -0.22
     Named
    -0.21
     wrote
    -0.20
     Designed
    -0.20
    Asked
    -0.19
     designed
    -0.19
     kill
    -0.18
     downgrade
    -0.18
    POSITIVE LOGITS
     deleted
    0.29
     withdrawn
    0.26
     altered
    0.26
     severed
    0.26
     destroyed
    0.25
     removed
    0.25
     changed
    0.24
     revoked
    0.24
    deleted
    0.24
    roken
    0.24
    Act Density 0.231%

    No Known Activations