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

    Neuronpedia

    INDEX
    Explanations

    references to actions involving removal or deletion

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

    "remove" or its variations

    np_acts-logits-general · gemini-2.0-flash

    removing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quién
    -0.57
    Cordialement
    -0.57
    اصمة
    -0.56
    ximity
    -0.55
    objPHPExcel
    -0.55
     חדש
    -0.55
     hausse
    -0.53
    Trả
    -0.53
    Amicalement
    -0.53
     Stuart
    -0.52
    POSITIVE LOGITS
     REMOVE
    1.12
     Removes
    1.06
     Remove
    1.05
     Removal
    1.03
     removes
    1.02
    REMOVE
    1.02
     remove
    1.02
     removal
    1.01
    AddTagHelper
    1.01
    Remove
    0.99
    Act Density 0.229%

    No Known Activations