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

    Neuronpedia

    INDEX
    Explanations

    expressions related to being attracted or drawn to something

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

    attracted to things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hyrchwyd
    -0.58
     MenuView
    -0.55
     kasarigan
    -0.50
     напо
    -0.49
    analog
    -0.49
    thansa
    -0.48
     pneum
    -0.47
    grano
    -0.47
     analog
    -0.46
     incompetent
    -0.46
    POSITIVE LOGITS
     attracted
    0.94
     attraction
    0.91
     atracción
    0.89
     attracts
    0.82
    attraction
    0.79
     Attra
    0.79
     Attraction
    0.79
     attract
    0.78
     attracting
    0.76
    Attra
    0.76
    Act Density 0.033%

    No Known Activations