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

    Neuronpedia

    INDEX
    Explanations

    indications of success or confirmation in messages

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

    Successfully created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.53
     فريبيس
    -0.45
    borderFill
    -0.44
    BeginContext
    -0.42
     curiosidad
    -0.41
    anyeol
    -0.41
    spender
    -0.40
    upaten
    -0.40
     Notwendigkeit
    -0.39
    Chham
    -0.39
    POSITIVE LOGITS
     successfully
    1.27
     Successfully
    1.13
     successful
    1.12
    Successfully
    1.08
    successfully
    1.04
     succes
    1.03
     Successful
    1.01
     success
    0.98
     sucess
    0.96
     SUCCESS
    0.94
    Act Density 0.020%

    No Known Activations