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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ethical considerations and judgments

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

    much more consistent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fprintf
    -0.38
    esomeness
    -0.37
    findpost
    -0.36
    }*/
    -0.34
    anair
    -0.34
    }*/
    -0.34
    ffet
    -0.33
     Oder
    -0.33
    }`}
    -0.33
     Spart
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.69
     فريبيس
    0.58
    ambién
    0.58
    tagHelperRunner
    0.54
    期刊论文
    0.51
    SharedCtor
    0.50
     صوتيه
    0.47
     charité
    0.47
    ۗ
    0.47
    aarrggbb
    0.46
    Act Density 0.248%

    No Known Activations