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

    Neuronpedia

    INDEX
    Explanations

    terms related to accusations or blame

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

    accusation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ausland
    -0.49
     Bingham
    -0.46
    orszá
    -0.45
     Waterman
    -0.45
     itinéraire
    -0.43
    StreetMap
    -0.43
    リエーション
    -0.42
    ︎
    -0.41
    Terra
    -0.41
    ровна
    -0.41
    POSITIVE LOGITS
     accused
    1.38
     accuse
    1.09
     accuses
    1.05
    accu
    1.02
     accusing
    0.97
     acusa
    0.75
     acusado
    0.75
     accus
    0.72
     hasattr
    0.69
     acus
    0.69
    Act Density 0.006%

    No Known Activations