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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "delete" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    delete club

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jîn
    -0.57
     Archer
    -0.48
     Goodman
    -0.48
    mbor
    -0.48
    Factor
    -0.47
     BCM
    -0.47
    workbench
    -0.46
     iface
    -0.46
     IW
    -0.46
    AXIS
    -0.46
    POSITIVE LOGITS
     delete
    1.68
    delete
    1.59
     Delete
    1.55
    Delete
    1.42
     DELETE
    1.38
     deletes
    1.29
    DELETE
    1.20
     deleting
    1.20
     Deleting
    1.18
     deletion
    1.16
    Act Density 0.010%

    No Known Activations