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

    Neuronpedia

    INDEX
    Explanations

    statements that express opposition or contradiction

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

    contrary to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.68
    parsedMessage
    -0.63
    inghouse
    -0.60
    providedIn
    -0.57
    reportWebVitals
    -0.57
     Normdatei
    -0.56
    CodedInputStream
    -0.56
     怎样
    -0.56
     noDo
    -0.55
     Theſe
    -0.55
    POSITIVE LOGITS
     contrary
    0.44
     contra
    0.42
    逆
    0.41
     Contrary
    0.40
     contre
    0.38
     entgegen
    0.38
     cuerdas
    0.38
    Contra
    0.38
    inverse
    0.38
     Contreras
    0.37
    Act Density 0.017%

    No Known Activations