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

    Neuronpedia

    INDEX
    Explanations

    references to investigations, legal proceedings, and political misconduct

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

    investigations or inquiries

    np_acts-logits-general · gemini-2.0-flash

    investigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.63
    EDEFAULT
    -0.54
    Clik
    -0.51
    KEYCODE
    -0.51
    Edy
    -0.48
     useDispatch
    -0.47
    cipar
    -0.47
     ekst
    -0.46
    BASELINE
    -0.46
    httphttps
    -0.45
    POSITIVE LOGITS
     investigation
    2.10
     investigations
    1.86
     investigating
    1.85
     probe
    1.77
     investigate
    1.77
    investigation
    1.75
     Investigation
    1.71
     investigates
    1.68
    investig
    1.67
    Investigation
    1.66
    Act Density 0.420%

    No Known Activations