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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional impact and supportive sentiments

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

    both alike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.47
    省市镇
    -0.44
    BufferException
    -0.43
    verifyException
    -0.40
    werfer
    -0.39
    FontOfSize
    -0.38
    draft
    -0.37
    balleur
    -0.37
     pega
    -0.36
    ussis
    -0.36
    POSITIVE LOGITS
     everyone
    0.62
     everybody
    0.59
     mutually
    0.58
    $_['
    0.54
    everyone
    0.51
     alike
    0.51
    Everybody
    0.50
    everybody
    0.50
    Everyone
    0.50
     Everyone
    0.49
    Act Density 0.053%

    No Known Activations