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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating an effort or initiative to influence or catalyze change

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

    pushing actions or ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.48
    ]='\
    -0.37
     snippetHide
    -0.36
     resident
    -0.35
    
    -0.35
     occasions
    -0.34
    ("}");
    -0.33
     escrit
    -0.31
     standing
    -0.30
    InjectAttribute
    -0.29
    POSITIVE LOGITS
     push
    1.27
    push
    1.06
     Push
    1.04
     PUSH
    1.02
     pushes
    1.00
     pushed
    0.99
    Push
    0.97
     pushing
    0.94
     Pushing
    0.92
    PUSH
    0.92
    Act Density 0.009%

    No Known Activations