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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate success or achievement

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

    success of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eratops
    -0.43
    platte
    -0.43
    ⟬
    -0.42
    blico
    -0.41
    psychiat
    -0.41
    Magick
    -0.40
    
    -0.40
     cubicle
    -0.40
    Einzelnachweise
    -0.40
     publiek
    -0.40
    POSITIVE LOGITS
     success
    0.88
     successful
    0.85
     Successful
    0.75
    successful
    0.73
     sucess
    0.72
     successes
    0.70
     SUCCESS
    0.69
     successo
    0.69
    Successful
    0.68
     éxito
    0.66
    Act Density 0.030%

    No Known Activations