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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers or negations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     विश्वसनीयता
    -0.79
     Normdatei
    -0.77
    AnimationsModule
    -0.76
     AssemblyCompany
    -0.74
     itſelf
    -0.73
    ⓧ
    -0.72
    tvguidetime
    -0.70
    tonode
    -0.69
    GetEnumerator
    -0.68
     OnTriggerEnter
    -0.67
    POSITIVE LOGITS
    wiada
    0.62
    +#+#
    0.59
    ်း
    0.58
     beszél
    0.52
    ്ട
    0.49
    ณ์
    0.48
    waite
    0.46
    ็จ
    0.46
     sais
    0.46
    nościo
    0.45
    Act Density 0.200%

    No Known Activations