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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choices

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

    Followed by "to" or "from"

    np_acts-logits-general · gemini-2.0-flash

    words followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.70
    EndInit
    -0.48
    Trax
    -0.48
    ніципалі
    -0.48
     بع
    -0.46
    |()
    -0.46
    のマ
    -0.44
     BnF
    -0.44
    ymi
    -0.43
    
    -0.43
    POSITIVE LOGITS
     withal
    1.01
     ifrån
    0.80
     ComVisible
    0.69
    setDo
    0.68
     igenom
    0.67
     commerciales
    0.65
     médicaux
    0.64
     utafitiHapana
    0.63
     religieuses
    0.63
    endpush
    0.62
    Act Density 0.237%

    No Known Activations