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

    Neuronpedia

    INDEX
    Explanations

    instances of criticism or negative evaluation of authority figures or societal issues

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

    allegationssanctionscriticised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁣
    -0.51
    HtmlAttribute
    -0.48
    InjectAttribute
    -0.41
    Personendaten
    -0.40
    SequentialGroup
    -0.39
     AssemblyTitle
    -0.39
     fieldNum
    -0.37
     صوتيه
    -0.36
     Taktlose
    -0.35
     autorytatywna
    -0.35
    POSITIVE LOGITS
     zuletzt
    0.46
     خارجية
    0.46
     برانيه
    0.41
     estekak
    0.40
    irvana
    0.39
    äj
    0.39
    stdc
    0.39
    omitempty
    0.38
     evermore
    0.38
    TabStop
    0.38
    Act Density 0.011%

    No Known Activations