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

    Neuronpedia

    INDEX
    Explanations

    issues related to customer service and complaints

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

    denial or rejection

    np_acts-logits-general · gemini-2.0-flash

    supposedly or allegedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Filmographie
    -0.57
    krok
    -0.54
     IMHO
    -0.53
    aarrggbb
    -0.52
     anthropo
    -0.52
     Martyrs
    -0.51
    inhard
    -0.50
    ibouti
    -0.50
     Recruitment
    -0.50
     تضيفلها
    -0.49
    POSITIVE LOGITS
     supuestamente
    0.69
     supposedly
    0.63
     allegedly
    0.54
     katanya
    0.52
    Apparently
    0.52
     refused
    0.52
     refunded
    0.49
     apparently
    0.48
     apologized
    0.48
     Apparently
    0.47
    Act Density 0.531%

    No Known Activations