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

    Neuronpedia

    INDEX
    Explanations

    phrases related to success and collaboration

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

    preceding beneficial outcomes or actions

    np_acts-logits-general · gemini-2.0-flash

    likelihood of positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AfterClass
    -0.55
    (!__
    -0.51
    しまいました
    -0.47
     Must
    -0.44
     need
    -0.44
    e
    -0.43
     Процитовано
    -0.43
    やや
    -0.43
    しまった
    -0.42
     via
    -0.42
    POSITIVE LOGITS
     happier
    0.83
     chances
    0.83
    ientôt
    0.78
     likelihood
    0.77
     itſelf
    0.76
     nämlich
    0.75
     healthier
    0.75
     Chances
    0.74
    verifyException
    0.74
     Likelihood
    0.74
    Act Density 0.251%

    No Known Activations