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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating accusation or blame

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

    accusing of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verrez
    -0.42
     korun
    -0.40
     issue
    -0.39
    Ainda
    -0.38
    decker
    -0.37
     the
    -0.36
    interno
    -0.36
    issue
    -0.35
     figliu
    -0.34
    taban
    -0.34
    POSITIVE LOGITS
    0.69
    andExpect
    0.66
     autorytatywna
    0.66
     utafitiHapana
    0.65
     guilty
    0.65
     мәкал
    0.63
     propOrder
    0.62
     Guilty
    0.62
    (&:
    0.61
    guilty
    0.60
    Act Density 0.020%

    No Known Activations