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

    Neuronpedia

    INDEX
    Explanations

    expressions related to helping and assisting others

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

    help someone out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kyse
    -0.38
     Metzger
    -0.38
     Krakowie
    -0.38
     innehå
    -0.37
     Gubernur
    -0.37
     Wachs
    -0.37
     lentejuelas
    -0.36
     asamblea
    -0.35
     Seitz
    -0.35
    ruecos
    -0.35
    POSITIVE LOGITS
    help
    1.09
    Help
    1.06
     Help
    1.05
    HELP
    1.01
     Helper
    0.98
     Helping
    0.96
     Aid
    0.96
    helping
    0.96
     Helpers
    0.94
    Helping
    0.93
    Act Density 0.038%

    No Known Activations