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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of desire or intent

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

    preceding a verb of permission/obligation

    np_acts-logits-general · gemini-2.0-flash

    being, having, getting, choosing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ustimmung
    -0.54
     Straß
    -0.51
    Odkazy
    -0.51
     возь
    -0.50
     zrobi
    -0.50
     Agreg
    -0.50
     rispond
    -0.49
     uzyska
    -0.49
     нажмите
    -0.48
    ronom
    -0.48
    POSITIVE LOGITS
     being
    1.03
     having
    0.92
     Being
    0.91
    being
    0.89
    Being
    0.89
     BEING
    0.81
     getting
    0.79
     choosing
    0.76
     doing
    0.76
     selecting
    0.76
    Act Density 0.071%

    No Known Activations