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

    Neuronpedia

    INDEX
    Explanations

    words expressing positivity or greetings

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

    Good followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.45
    rungsseite
    -0.42
    ябре
    -0.41
    dule
    -0.38
     Access
    -0.37
    tissement
    -0.37
    Biographie
    -0.37
     internally
    -0.36
     Celle
    -0.36
     access
    -0.35
    POSITIVE LOGITS
    Good
    0.99
     Good
    0.93
    GOOD
    0.85
     GOOD
    0.83
    good
    0.82
     good
    0.81
     dobré
    0.73
     buenas
    0.68
     goede
    0.68
     bonnes
    0.66
    Act Density 0.011%

    No Known Activations