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

    Neuronpedia

    INDEX
    Explanations

    distinct tokens with high-frequency attributes

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

    ot followed by .f or ONIC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FormGroup
    -0.51
     zijne
    -0.50
     startX
    -0.50
     dezelve
    -0.49
    ChildScrollView
    -0.49
     zoude
    -0.48
     indépendante
    -0.48
    /*
    -0.46
    puma
    -0.46
    Karriere
    -0.46
    POSITIVE LOGITS
    ot
    2.52
    OT
    1.89
     ot
    1.44
    ots
    1.40
     OT
    1.38
    Ot
    1.33
     Ot
    1.27
    yot
    1.06
    от
    1.02
    OTS
    1.02
    Act Density 0.015%

    No Known Activations