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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or criticisms presented in sentences

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

    hyper-responsiveness or substituted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientras
    -0.88
     plufieurs
    -0.87
     للمعارف
    -0.86
    ſcher
    -0.85
     queſta
    -0.82
     ſont
    -0.76
     myſelf
    -0.75
    ſſel
    -0.75
     beſch
    -0.74
    ésultats
    -0.73
    POSITIVE LOGITS
     and
    0.40
    ·
    0.38
     or
    0.38
    、
    0.37
    •
    0.35
    –
    0.34
     of
    0.33
    ↵
    0.33
     amongst
    0.32
    -,
    0.32
    Act Density 0.185%

    No Known Activations