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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity or praise

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

    good followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souha
    -0.38
    Personendaten
    -0.38
     menger
    -0.37
    }],
    -0.37
     fís
    -0.37
     mora
    -0.37
     szeret
    -0.36
    ]));
    -0.36
     arac
    -0.35
     Fa
    -0.35
    POSITIVE LOGITS
    PullParser
    0.57
    GraphicsUnit
    0.54
     Gaulle
    0.48
    лтемелер
    0.47
     fuckin
    0.47
    fucker
    0.47
    antd
    0.47
    😜
    0.46
     iParam
    0.45
     OKAY
    0.45
    Act Density 0.064%

    No Known Activations